diff --git a/translations/fi/.co-op-translator.json b/translations/fi/.co-op-translator.json
new file mode 100644
index 00000000..8cc5e079
--- /dev/null
+++ b/translations/fi/.co-op-translator.json
@@ -0,0 +1,398 @@
+{
+ "AGENTS.md": {
+ "original_hash": "6b11a37115944252ab3ed04e358d830d",
+ "translation_date": "2025-10-03T09:23:56+00:00",
+ "source_file": "AGENTS.md",
+ "language_code": "fi"
+ },
+ "README.md": {
+ "original_hash": "1984fc89dd304a8a33ab5584691a99aa",
+ "translation_date": "2026-01-30T02:05:49+00:00",
+ "source_file": "README.md",
+ "language_code": "fi"
+ },
+ "SECURITY.md": {
+ "original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
+ "translation_date": "2025-08-28T19:13:19+00:00",
+ "source_file": "SECURITY.md",
+ "language_code": "fi"
+ },
+ "etc/CODE_OF_CONDUCT.md": {
+ "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
+ "translation_date": "2025-08-28T20:13:19+00:00",
+ "source_file": "etc/CODE_OF_CONDUCT.md",
+ "language_code": "fi"
+ },
+ "etc/CONTRIBUTING.md": {
+ "original_hash": "847a587aa1b83f4d00858183ff3ed18a",
+ "translation_date": "2025-08-28T20:12:52+00:00",
+ "source_file": "etc/CONTRIBUTING.md",
+ "language_code": "fi"
+ },
+ "etc/Mindmap.md": {
+ "original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
+ "translation_date": "2025-08-28T20:10:41+00:00",
+ "source_file": "etc/Mindmap.md",
+ "language_code": "fi"
+ },
+ "etc/SUPPORT.md": {
+ "original_hash": "fdfc08baee91e402938a2b1f94fe0949",
+ "translation_date": "2025-08-28T20:10:02+00:00",
+ "source_file": "etc/SUPPORT.md",
+ "language_code": "fi"
+ },
+ "etc/TRANSLATIONS.md": {
+ "original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
+ "translation_date": "2025-08-28T20:12:25+00:00",
+ "source_file": "etc/TRANSLATIONS.md",
+ "language_code": "fi"
+ },
+ "etc/quiz-app/README.md": {
+ "original_hash": "d699cf8509f74baa5b0b838de5cf0662",
+ "translation_date": "2025-08-28T20:13:36+00:00",
+ "source_file": "etc/quiz-app/README.md",
+ "language_code": "fi"
+ },
+ "examples/README.md": {
+ "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
+ "translation_date": "2025-10-03T11:31:51+00:00",
+ "source_file": "examples/README.md",
+ "language_code": "fi"
+ },
+ "lessons/0-course-setup/for-teachers.md": {
+ "original_hash": "a094ef9927883de1cfcee51dbd143381",
+ "translation_date": "2025-08-28T19:18:56+00:00",
+ "source_file": "lessons/0-course-setup/for-teachers.md",
+ "language_code": "fi"
+ },
+ "lessons/0-course-setup/how-to-run.md": {
+ "original_hash": "a4717bd9103b9f6cd84d534b83534689",
+ "translation_date": "2026-01-16T02:59:25+00:00",
+ "source_file": "lessons/0-course-setup/how-to-run.md",
+ "language_code": "fi"
+ },
+ "lessons/0-course-setup/setup.md": {
+ "original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
+ "translation_date": "2025-12-12T19:55:12+00:00",
+ "source_file": "lessons/0-course-setup/setup.md",
+ "language_code": "fi"
+ },
+ "lessons/1-Intro/README.md": {
+ "original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
+ "translation_date": "2025-11-18T21:39:06+00:00",
+ "source_file": "lessons/1-Intro/README.md",
+ "language_code": "fi"
+ },
+ "lessons/1-Intro/assignment.md": {
+ "original_hash": "a334df77a82aaaf2a29c77065d3e481e",
+ "translation_date": "2025-11-18T21:40:42+00:00",
+ "source_file": "lessons/1-Intro/assignment.md",
+ "language_code": "fi"
+ },
+ "lessons/2-Symbolic/README.md": {
+ "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
+ "translation_date": "2026-01-16T02:59:45+00:00",
+ "source_file": "lessons/2-Symbolic/README.md",
+ "language_code": "fi"
+ },
+ "lessons/2-Symbolic/assignment.md": {
+ "original_hash": "a057a8604f3976c3e309884453f1fad0",
+ "translation_date": "2025-08-28T19:41:09+00:00",
+ "source_file": "lessons/2-Symbolic/assignment.md",
+ "language_code": "fi"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/README.md": {
+ "original_hash": "c34cbba802058b6fa267e1a294d4e510",
+ "translation_date": "2025-09-23T10:01:55+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
+ "language_code": "fi"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
+ "original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
+ "translation_date": "2025-08-29T11:39:45+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
+ "original_hash": "789d6c3fb6fc7948a470b33078a5983a",
+ "translation_date": "2025-09-23T10:01:32+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
+ "language_code": "fi"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
+ "original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
+ "translation_date": "2025-08-28T19:47:36+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/README.md": {
+ "original_hash": "ddd216f558a255260a9374008002c971",
+ "translation_date": "2025-09-23T10:02:17+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
+ "language_code": "fi"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
+ "original_hash": "e452d897efb9a89700f41021834cf6e5",
+ "translation_date": "2025-08-28T19:50:49+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/3-NeuralNetworks/README.md": {
+ "original_hash": "f862a99d88088163df12270e2f2ad6c3",
+ "translation_date": "2025-10-03T12:50:05+00:00",
+ "source_file": "lessons/3-NeuralNetworks/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/README.md": {
+ "original_hash": "feeca98225cb420afc89415f24f63d92",
+ "translation_date": "2025-09-23T09:57:04+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
+ "original_hash": "3d53d6409f80970f7281a45dee35328a",
+ "translation_date": "2025-08-28T19:31:17+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
+ "original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
+ "translation_date": "2025-09-23T09:56:27+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/README.md": {
+ "original_hash": "a560d5b845962cf33dc102266e409568",
+ "translation_date": "2025-09-23T09:56:03+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
+ "original_hash": "b70fcf7fcee862990f848c679090943f",
+ "translation_date": "2025-10-03T14:55:46+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/README.md": {
+ "original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
+ "translation_date": "2025-09-23T09:56:44+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
+ "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
+ "translation_date": "2025-08-28T19:27:42+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
+ "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
+ "translation_date": "2025-08-28T19:29:15+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/09-Autoencoders/README.md": {
+ "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
+ "translation_date": "2025-09-23T09:58:20+00:00",
+ "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/10-GANs/README.md": {
+ "original_hash": "0ff65b4da07b23697235de2beb2a3c25",
+ "translation_date": "2025-09-23T09:59:02+00:00",
+ "source_file": "lessons/4-ComputerVision/10-GANs/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/README.md": {
+ "original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
+ "translation_date": "2025-09-23T09:57:41+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
+ "original_hash": "ad568d55ae65c856fe929fc2b278510a",
+ "translation_date": "2025-08-28T19:33:17+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/README.md": {
+ "original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
+ "translation_date": "2025-09-23T09:58:48+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
+ "original_hash": "365f0decfe0f47b460bbde8227c5009d",
+ "translation_date": "2025-08-28T19:36:28+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/4-ComputerVision/README.md": {
+ "original_hash": "58a52f000089c1d8906a4daa4ab1169b",
+ "translation_date": "2025-08-28T19:23:18+00:00",
+ "source_file": "lessons/4-ComputerVision/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/13-TextRep/README.md": {
+ "original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
+ "translation_date": "2025-09-23T10:05:19+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/13-TextRep/assignment.md": {
+ "original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
+ "translation_date": "2025-08-28T20:09:46+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/assignment.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/14-Embeddings/README.md": {
+ "original_hash": "b708c9b85b833864c73c6281f1e6b96e",
+ "translation_date": "2025-09-23T10:04:58+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/14-Embeddings/assignment.md": {
+ "original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
+ "translation_date": "2025-08-28T20:08:21+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/15-LanguageModeling/README.md": {
+ "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
+ "translation_date": "2025-09-23T10:03:10+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/15-LanguageModeling/lab/README.md": {
+ "original_hash": "5130f01fdc5ebb83032b23d489027aac",
+ "translation_date": "2025-08-28T20:00:35+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/16-RNN/README.md": {
+ "original_hash": "e2273cc150380a5e191903cea858f021",
+ "translation_date": "2025-09-23T10:04:31+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/16-RNN/assignment.md": {
+ "original_hash": "47f7d3c6a5373543e051e4d1140ce898",
+ "translation_date": "2025-08-28T20:07:05+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/assignment.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/README.md": {
+ "original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
+ "translation_date": "2025-09-23T10:02:43+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
+ "original_hash": "439e12796197a90e7623d4c9c057b9c2",
+ "translation_date": "2025-08-28T19:59:38+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/18-Transformers/README.md": {
+ "original_hash": "f335dfcb4a993920504c387973a36957",
+ "translation_date": "2025-09-23T10:03:21+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/18-Transformers/assignment.md": {
+ "original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
+ "translation_date": "2025-08-28T20:02:35+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/assignment.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/19-NER/README.md": {
+ "original_hash": "6522312ff835796ca34136a9462fafb2",
+ "translation_date": "2025-09-23T10:04:10+00:00",
+ "source_file": "lessons/5-NLP/19-NER/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/19-NER/lab/README.md": {
+ "original_hash": "032bda5068f543d6c1fcb30c34231461",
+ "translation_date": "2025-08-28T20:04:56+00:00",
+ "source_file": "lessons/5-NLP/19-NER/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/20-LangModels/README.md": {
+ "original_hash": "97836d30a6bec736f8e3b4411c572bc2",
+ "translation_date": "2025-09-23T10:03:49+00:00",
+ "source_file": "lessons/5-NLP/20-LangModels/README.md",
+ "language_code": "fi"
+ },
+ "lessons/5-NLP/README.md": {
+ "original_hash": "8ef02a9318257ea140ed3ed74442096d",
+ "translation_date": "2025-08-28T19:56:47+00:00",
+ "source_file": "lessons/5-NLP/README.md",
+ "language_code": "fi"
+ },
+ "lessons/6-Other/21-GeneticAlgorithms/README.md": {
+ "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
+ "translation_date": "2025-09-23T09:54:15+00:00",
+ "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
+ "language_code": "fi"
+ },
+ "lessons/6-Other/22-DeepRL/README.md": {
+ "original_hash": "04395657fc01648f8f70484d0e55ab67",
+ "translation_date": "2025-09-23T09:55:16+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/README.md",
+ "language_code": "fi"
+ },
+ "lessons/6-Other/22-DeepRL/lab/README.md": {
+ "original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
+ "translation_date": "2025-08-28T19:18:37+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
+ "language_code": "fi"
+ },
+ "lessons/6-Other/23-MultiagentSystems/README.md": {
+ "original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
+ "translation_date": "2025-09-23T09:54:34+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
+ "language_code": "fi"
+ },
+ "lessons/6-Other/23-MultiagentSystems/assignment.md": {
+ "original_hash": "cf654ca60c7f86c8dad28596fb42994b",
+ "translation_date": "2025-08-28T19:16:56+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
+ "language_code": "fi"
+ },
+ "lessons/7-Ethics/README.md": {
+ "original_hash": "437c988596e751072e41a5aad3fcc5d9",
+ "translation_date": "2025-08-28T19:41:27+00:00",
+ "source_file": "lessons/7-Ethics/README.md",
+ "language_code": "fi"
+ },
+ "lessons/README.md": {
+ "original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
+ "translation_date": "2025-08-28T19:13:56+00:00",
+ "source_file": "lessons/README.md",
+ "language_code": "fi"
+ },
+ "lessons/X-Extras/X1-MultiModal/README.md": {
+ "original_hash": "9c592c26aca16ca085d268c732284187",
+ "translation_date": "2025-08-28T19:21:33+00:00",
+ "source_file": "lessons/X-Extras/X1-MultiModal/README.md",
+ "language_code": "fi"
+ },
+ "lessons/sketchnotes/LICENSE.md": {
+ "original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
+ "translation_date": "2025-08-28T19:52:34+00:00",
+ "source_file": "lessons/sketchnotes/LICENSE.md",
+ "language_code": "fi"
+ },
+ "lessons/sketchnotes/README.md": {
+ "original_hash": "050b8bddebafba55b129414e6ab096ab",
+ "translation_date": "2025-08-28T19:51:12+00:00",
+ "source_file": "lessons/sketchnotes/README.md",
+ "language_code": "fi"
+ },
+ "troubleshoot.md": {
+ "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
+ "translation_date": "2025-10-03T09:46:08+00:00",
+ "source_file": "troubleshoot.md",
+ "language_code": "fi"
+ }
+}
\ No newline at end of file
diff --git a/translations/fi/AGENTS.md b/translations/fi/AGENTS.md
index 6c1a7b50..895d29f3 100644
--- a/translations/fi/AGENTS.md
+++ b/translations/fi/AGENTS.md
@@ -1,12 +1,3 @@
-
# AGENTS.md
## Projektin yleiskatsaus
diff --git a/translations/fi/README.md b/translations/fi/README.md
index 6cce3e52..75ee6d10 100644
--- a/translations/fi/README.md
+++ b/translations/fi/README.md
@@ -1,12 +1,3 @@
-
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@@ -21,33 +12,34 @@ CO_OP_TRANSLATOR_METADATA:
[](https://discord.gg/nTYy5BXMWG)
-# Tekoäly aloittelijoille - Opetussuunnitelma
+# Tekoäly Aloittelijoille - Opintokokonaisuus
-||
+||
|:---:|
-| AI Aloittelijoille - _Sketchnote tekijältä [@girlie_mac](https://twitter.com/girlie_mac)_ |
+| AI Aloittelijoille - _Sketchnote kirjoittanut [@girlie_mac](https://twitter.com/girlie_mac)_ |
+
+Tutustu **Tekoälyn** (AI) maailmaan 12 viikon ja 24 oppitunnin kurssikokonaisuudellamme! Se sisältää käytännön oppitunteja, tietovisat ja laboratoriotöitä. Kurssi on aloittelijaystävällinen ja kattaa työkaluja kuten TensorFlow ja PyTorch sekä tekoälyn eettiset kysymykset.
-Tutustu **tekoälyn** (AI) maailmaan 12 viikon, 24 oppitunnin opetussuunnitelmamme avulla! Sisältää käytännön tehtäviä, tietovisoja ja laboratoriotöitä. Opetussuunnitelma on aloittelijaystävällinen ja kattaa työkalut kuten TensorFlow ja PyTorch sekä tekoälyn etiikan.
### 🌐 Monikielinen tuki
-#### Tuettu GitHub Actionin avulla (automaattinen ja aina ajan tasalla)
+#### Tuettu GitHub Actionin kautta (Automaattinen & aina ajan tasalla)
-[Arabia](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgaria](../bg/README.md) | [Burma (Myanmar)](../my/README.md) | [Kiina (yksinkertaistettu)](../zh/README.md) | [Kiina (perinteinen, Hong Kong)](../hk/README.md) | [Kiina (perinteinen, Macao)](../mo/README.md) | [Kiina (perinteinen, Taiwan)](../tw/README.md) | [Kroatia](../hr/README.md) | [Tšekki](../cs/README.md) | [Tanska](../da/README.md) | [Hollanti](../nl/README.md) | [Viro](../et/README.md) | [Suomi](./README.md) | [Ranska](../fr/README.md) | [Saksa](../de/README.md) | [Kreikka](../el/README.md) | [Heprea](../he/README.md) | [Hindi](../hi/README.md) | [Unkari](../hu/README.md) | [Indonesia](../id/README.md) | [Italia](../it/README.md) | [Japani](../ja/README.md) | [Kannada](../kn/README.md) | [Korea](../ko/README.md) | [Liettua](../lt/README.md) | [Malaiji](../ms/README.md) | [Malajalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norja](../no/README.md) | [Persia (Farsi)](../fa/README.md) | [Puola](../pl/README.md) | [Portugali (Brasilia)](../br/README.md) | [Portugali (Portugali)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romania](../ro/README.md) | [Venäjä](../ru/README.md) | [Serbia (kyrillinen)](../sr/README.md) | [Slovakki](../sk/README.md) | [Sloveeni](../sl/README.md) | [Espanja](../es/README.md) | [Swahili](../sw/README.md) | [Ruotsi](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamili](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkki](../tr/README.md) | [Ukraina](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnam](../vi/README.md)
+[Arabia](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgaria](../bg/README.md) | [Burma (Myanmar)](../my/README.md) | [Kiina (yksinkertaistettu)](../zh-CN/README.md) | [Kiina (perinteinen, Hong Kong)](../zh-HK/README.md) | [Kiina (perinteinen, Macau)](../zh-MO/README.md) | [Kiina (perinteinen, Taiwan)](../zh-TW/README.md) | [Kroatia](../hr/README.md) | [Tšekki](../cs/README.md) | [Tanska](../da/README.md) | [Hollanti](../nl/README.md) | [Viro](../et/README.md) | [Suomi](./README.md) | [Ranska](../fr/README.md) | [Saksa](../de/README.md) | [Kreikka](../el/README.md) | [Heprea](../he/README.md) | [Hindi](../hi/README.md) | [Unkari](../hu/README.md) | [Indonesia](../id/README.md) | [Italia](../it/README.md) | [Japani](../ja/README.md) | [Kannada](../kn/README.md) | [Korea](../ko/README.md) | [Liettua](../lt/README.md) | [Malaiji](../ms/README.md) | [Malajalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norja](../no/README.md) | [Persia (Farsi)](../fa/README.md) | [Puola](../pl/README.md) | [Portugali (Brasilia)](../pt-BR/README.md) | [Portugali (Portugali)](../pt-PT/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romania](../ro/README.md) | [Venäjä](../ru/README.md) | [Serbia (kyrillinen)](../sr/README.md) | [Slovakki](../sk/README.md) | [Sloveeni](../sl/README.md) | [Espanja](../es/README.md) | [Swahili](../sw/README.md) | [Ruotsi](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkki](../tr/README.md) | [Ukraina](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnam](../vi/README.md)
-> **Haluatko mieluummin kloonata paikallisesti?**
+> **Haluatko kloonata paikallisesti?**
-> Tässä arkistossa on yli 50 kielen käännökset, jotka kasvattavat merkittävästi latauskokoa. Jos haluat kloonata ilman käännöksiä, käytä sparse checkoutia:
+> Tämä arkisto sisältää 50+ käännöskieltä, mikä lisää merkittävästi latauskokoa. Kloonaa ilman käännöksiä käyttämällä sparse checkout -ominaisuutta:
> ```bash
> git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git
> cd AI-For-Beginners
> git sparse-checkout set --no-cone '/*' '!translations' '!translated_images'
> ```
-> Tämä antaa sinulle kaiken, mitä tarvitset kurssin suorittamiseen paljon nopeammalla latauksella.
+> Tämä tarjoaa kaiken tarvittavan kurssin suorittamiseen huomattavasti nopeammalla latauksella.
-**Jos haluat lisäkieliä käännöksiksi, tuetut kielet löytyvät [täältä](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
+**Jos haluat lisää tuettuja käännöskieliä, ne on listattu [tässä](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
## Liity yhteisöön
[](https://discord.gg/nTYy5BXMWG)
@@ -56,177 +48,178 @@ Tutustu **tekoälyn** (AI) maailmaan 12 viikon, 24 oppitunnin opetussuunnitelmam
**[Kurssin miellekartta](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
-Tässä opetussuunnitelmassa opit:
+Tässä opintokokonaisuudessa opit:
-* Eri lähestymistapoja tekoälyyn, mukaan lukien "hyvä vanha" symbolinen lähestymistapa **Tietämyksen esittämisen** ja päättelyn kanssa ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
-* **Neuroverkkoja** ja **Syväoppimista**, jotka ovat modernin tekoälyn ytimessä. Havainnollistamme näiden tärkeiden aiheiden taustalla olevia käsitteitä käyttämällä kahta suosittua kehystä - [TensorFlow](http://Tensorflow.org) ja [PyTorch](http://pytorch.org).
-* **Neuroarkkitehtuureja** kuvan ja tekstin käsittelyyn. Käymme läpi uusia malleja, mutta saatamme olla hieman jäljessä viimeisimmästä kehityksestä.
-* Vähemmän suosittuja tekoälyn lähestymistapoja, kuten **Geneettisiä algoritmeja** ja **Moni-agenttijärjestelmiä**.
+* Eri lähestymistapoja tekoälyyn, mukaan lukien "hyvä vanha" symbolinen lähestymistapa, joka käyttää **Tietojen esitystä** ja päättelyä ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
+* **Neuroverkot** ja **Syväoppiminen**, jotka ovat nykyaikaisen tekoälyn ydintä. Käytämme kahta suosittua kehystä - [TensorFlow](http://Tensorflow.org) ja [PyTorch](http://pytorch.org) - havainnollistamaan näihin aiheisiin liittyviä käsitteitä koodin avulla.
+* **Neuroarkkitehtuurit** kuvan- ja tekstinkäsittelyyn. Käymme läpi viimeisimpiä malleja, vaikka ne eivät aina edusta aivan uusinta teknologiaa.
+* Vähemmän tunnettuja tekoälyn lähestymistapoja, kuten **Geneettisiä algoritmeja** ja **Moni-agenttijärjestelmiä**.
-Mitä emme käsittele tässä opetussuunnitelmassa:
+Mitä emme käsittele tässä opintokokonaisuudessa:
-> [Löydä kaikki tämän kurssin lisäresurssit Microsoft Learn -kokoelmastamme](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
+> [Löydä kaikki tämän kurssin lisämateriaalit Microsoft Learn -kokoelmastamme](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
-* Liiketoiminnan käyttötapauksia, joissa hyödynnetään **tekoälyä liiketoiminnassa**. Suosittelemme tutustumaan Microsoft Learnin [Johdatus tekoälyyn liiketoiminnan käyttäjille](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) oppimispolkuun tai [AI Business Schooliin](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), joka on kehitetty yhteistyössä [INSEADin](https://www.insead.edu/) kanssa.
-* **Perinteistä koneoppimista**, joka on hyvin kuvattu opetussuunnitelmassamme [Machine Learning for Beginners](http://github.com/Microsoft/ML-for-Beginners).
-* Käytännön tekoälysovelluksia, jotka on rakennettu käyttäen **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** -palveluita. Tätä varten suosittelemme aloittamaan Microsoft Learnin moduuleista näköaistilla ([vision](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum)), luonnollisen kielen prosessoinnilla ([natural language processing](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum)), **[Generatiivisella tekoälyllä Azure OpenAI -palvelulla](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ja muilla.
-* Tiettyjä ML **pilvikehyksiä**, kuten [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), tai [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Otamme huomioon [Rakenna ja hallinnoi koneoppimisratkaisuja Azure Machine Learningilla](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) ja [Rakenna ja hallinnoi koneoppimisratkaisuja Azure Databricksilla](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum) oppimispolut.
-* **Keskustelullista tekoälyä** ja **chatbotteja**. Näihin on oma [Luo keskustelullisia tekoälyratkaisuja](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) oppimispolkunsa, ja tarkempaa tietoa löydät myös [tästä blogikirjoituksesta](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/).
-* **Syvä matematiikka** syväoppimisen taustalla. Tätä varten suosittelemme Ian Goodfellow'n, Yoshua Bengion ja Aaron Courvillen teosta [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618), joka on myös saatavilla verkossa osoitteessa [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
+* Liiketoimintatapauksia **tekoälyn käytöstä liiketoiminnassa**. Suosittelemme ottamaan [Johdanto tekoälyyn liiketoiminnan käyttäjille](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) -oppimispolun Microsoft Learnissa tai [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), joka on kehitetty yhteistyössä [INSEADin](https://www.insead.edu/) kanssa.
+* **Klassista koneoppimista**, jota käsitellään hyvin [Koneoppiminen aloittelijoille](http://github.com/Microsoft/ML-for-Beginners) -opintokokonaisuudessamme.
+* Käytännön tekoälysovelluksia, jotka on rakennettu käyttäen **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)** -palveluita. Tässä suosittelemme aloittamaan Microsoft Learn -moduuleista [näköaistille](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [luonnollisen kielen käsittelyyn](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generatiiviseen tekoälyyn Azure OpenAI -palvelulla](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** ja muihin.
+* Erityisiä ML **pilvikehyksiä**, kuten [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum) tai [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Harkitse käyttäväsi oppimispolkuja [Machine Learning -ratkaisujen rakentaminen ja käyttöönotto Azure Machine Learningillä](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) ja [Machine Learning -ratkaisujen rakentaminen ja toimintakuntoon Azure Databricksillä](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
+* **Keskusteluperusteinen tekoäly** ja **Chataobotit**. Niihin on oma [Luo keskusteluperusteisia tekoälyratkaisuja](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) -oppimispolkunsa, ja lisätietoa löydät myös [tästä blogikirjoituksesta](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/).
+* **Syvällinen matematiikka** syväoppimisen takana. Tässä suosittelemme teosta [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) kirjoittanut Ian Goodfellow, Yoshua Bengio ja Aaron Courville, joka on saatavilla myös netissä osoitteessa [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
-Matala-asteinen johdanto _tekoälyyn pilvessä_ -aiheisiin löytyy Microsoft Leanin [Aloita tekoälyn kanssa Azurella](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) - oppimispolulta.
+Hellävaraisemman johdannon _tekoälystä pilvessä_ aiheisiin saa ottamalla [Aloita tekoälyn kanssa Azurella](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) -oppimispolun.
# Sisältö
-| | Oppitunnin linkki | PyTorch/Keras/TensorFlow | Lab |
+| | Oppitunnin linkki | PyTorch/Keras/TensorFlow | Labra |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
-| 0 | [Kurssin asetukset](./lessons/0-course-setup/setup.md) | [Ota kehitysympäristö käyttöön](./lessons/0-course-setup/how-to-run.md) | |
+| 0 | [Kurssin aloitus](./lessons/0-course-setup/setup.md) | [Kehitysympäristön asennus](./lessons/0-course-setup/how-to-run.md) | |
| I | [**Johdatus tekoälyyn**](./lessons/1-Intro/README.md) | | |
| 01 | [Johdanto ja tekoälyn historia](./lessons/1-Intro/README.md) | - | - |
-| II | **Sykolinen tekoäly** |
-| 02 | [Tietämyksen esittäminen ja asiantuntijajärjestelmät](./lessons/2-Symbolic/README.md) | [Asiantuntijajärjestelmät](./lessons/2-Symbolic/Animals.ipynb) / [Ontologia](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Käsiteverkko](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
+| II | **Symbolinen tekoäly** |
+| 02 | [Tietojen esitys ja asiantuntijajärjestelmät](./lessons/2-Symbolic/README.md) | [Asiantuntijajärjestelmät](./lessons/2-Symbolic/Animals.ipynb) / [Ontologia](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Käsitteiden verkko](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Johdatus neuroverkkoihin**](./lessons/3-NeuralNetworks/README.md) |||
-| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Notebook](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Lab](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
-| 04 | [Monikerroksinen Perceptron ja Oman Kehyksen Luominen](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notebook](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
-| 05 | [Johdanto kehyksiin (PyTorch/TensorFlow) ja Ylilyönti](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
-| IV | [**Tietokonenäkö**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Tutustu tietokonenäköön Microsoft Azurella](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
-| 06 | [Johdanto tietokonenäköön. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notebook](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
-| 07 | [Konvoluutioneuroverkot](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN-arkkitehtuurit](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Lab](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
-| 08 | [Esikoulutetut verkot ja siirto-oppiminen](./lessons/4-ComputerVision/08-TransferLearning/README.md) ja [Koulutusvinkit](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
+| 03 | [Perceptroni](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Muistikirja](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Labra](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
+| 04 | [Monikerroksinen perceptroni ja oman kehyskirjaston luominen](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Muistikirja](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Labra](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
+| 05 | [Johdatus kehyksiin (PyTorch/TensorFlow) ja ylisovittaminen](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Labra](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
+| IV | [**Tietokonenäkö**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Tutustu tietokonenäköön Microsoft Azuren avulla](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
+| 06 | [Johdatus tietokonenäköön. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Muistikirja](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Labra](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
+| 07 | [Konvoluutiohermoverkot](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN-arkkitehtuurit](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Labra](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
+| 08 | [Esikoulutetut verkot ja siirtovaikuttaminen](./lessons/4-ComputerVision/08-TransferLearning/README.md) ja [Koulutusvinkit](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Labra](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
| 09 | [Autoenkooderit ja VAE:t](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
-| 10 | [Generatiiviset vastakkainasettelumallit ja taiteellinen siirto](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
-| 11 | [Kohteen tunnistus](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Lab](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
+| 10 | [Generatiiviset vihollisverkot & taiteen tyylinsiirto](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
+| 11 | [Kohteiden tunnistus](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Labra](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
| 12 | [Semanttinen segmentointi. U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | |
-| V | [**Luonnollisen kielen käsittely**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Tutustu luonnollisen kielen käsittelyyn Microsoft Azurella](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
+| V | [**Luonnollisen kielen käsittely**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Tutustu luonnollisen kielen käsittelyyn Microsoft Azuren avulla](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Tekstin esitys. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | |
-| 14 | [Semanttiset sanasijoitukset. Word2Vec ja GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
-| 15 | [Kielimallinnus. Oman upotuksen kouluttaminen](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
-| 16 | [Toistuvat neuroverkot](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | |
-| 17 | [Generatiiviset toistuvat verkot](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [Lab](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
-| 18 | [Transformers. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | |
-| 19 | [Nimettyjen entiteettien tunnistus](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Lab](./lessons/5-NLP/19-NER/lab/README.md) |
-| 20 | [Laajat kielimallit, kehotteiden ohjelmointi ja vähäiset oppimistehtävät](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
+| 14 | [Semanttiset sanansaadot. Word2Vec ja GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
+| 15 | [Kielimallinnus. Omien upotusten harjoittaminen](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Labra](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
+| 16 | [Takaisinkytketyt neuroverkot](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | |
+| 17 | [Generatiiviset takaisinkytketyt verkot](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [Labra](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
+| 18 | [Transformaattorit. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | |
+| 19 | [Nimettyjen entiteettien tunnistus](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Labra](./lessons/5-NLP/19-NER/lab/README.md) |
+| 20 | [Suuret kielimallit, kehotusohjelmointi ja vähän.esimerkkitehtäviä](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| VI | **Muut tekoälytekniikat** || |
-| 21 | [Geneettiset algoritmit](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
-| 22 | [Syvävahvistusoppiminen](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) |
+| 21 | [Geneettiset algoritmit](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Muistikirja](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
+| 22 | [Syvä vahvistusoppiminen](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Labra](./lessons/6-Other/22-DeepRL/lab/README.md) |
| 23 | [Moniagenttijärjestelmät](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
| VII | **Tekoälyn etiikka** | | |
| 24 | [Tekoälyn etiikka ja vastuullinen tekoäly](./lessons/7-Ethics/README.md) | [Microsoft Learn: Vastuullisen tekoälyn periaatteet](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
-| IX | **Lisää** | | |
-| 25 | [Monimodaaliset verkot, CLIP ja VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
+| IX | **Lisäaineistot** | | |
+| 25 | [Monimodaaliset verkot, CLIP ja VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Muistikirja](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
## Jokainen oppitunti sisältää
-* Ennakkolukemista materiaalia
-* Suoritettavia Jupyter-muistikirjoja, jotka ovat usein kehyspohjaisia (**PyTorch** tai **TensorFlow**). Suoritettava muistikirja sisältää myös paljon teoreettista materiaalia, joten aiheen ymmärtämiseksi sinun täytyy käydä läpi ainakin yksi versio muistikirjasta (PyTorch tai TensorFlow).
-* **Labroja** tarjolla joillekin aiheille, jotka antavat sinulle mahdollisuuden kokeilla oppimaasi käytännössä tietyn ongelman ratkaisemiseksi.
-* Joissakin osioissa on linkkejä [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) -moduuleihin, jotka käsittelevät aiheeseen liittyviä aiheita.
+* Ennakko-lukemateriaalia
+* Suoritettavia Jupyter-muistikirjoja, jotka ovat usein spesifisiä kehykselle (**PyTorch** tai **TensorFlow**). Suoritettava muistikirja sisältää myös paljon teoreettista aineistoa, joten aiheen ymmärtämiseksi sinun tulee käydä läpi ainakin jokin muistikirjan versioista (joko PyTorch tai TensorFlow).
+* **Labroja** joihinkin aiheisiin, jotka antavat sinulle mahdollisuuden kokeilla oppimaasi käytännössä tietyn ongelman ratkaisemiseksi.
+* Joihinkin osioihin sisältyy linkkejä [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) moduuleihin, jotka käsittelevät aiheeseen liittyviä teemoja.
-## Aloittaminen
+## Alkuun pääseminen
-### 🎯 Uusi tekoälyssä? Aloita tästä!
+### 🎯 Uusi tekoälyn parissa? Aloita tästä!
-Jos olet täysin uusi tekoälyssä ja haluat nopeita, käytännön esimerkkejä, tutustu [**Aloittelijaystävällisiin esimerkkeihin**](./examples/README.md)! Näihin sisältyy:
+Jos olet täysin uusi tekoälyn parissa ja haluat nopeita, käytännön esimerkkejä, tutustu [**aloittelijaystävällisiin esimerkkeihimme**](./examples/README.md)! Niihin sisältyy:
-- 🌟 **Hei tekoälymaailma** - Ensimmäinen tekoälyohjelmasi (kuvion tunnistus)
-- 🧠 **Yksinkertainen neuroverkko** - Luo neuroverkko alusta alkaen
-- 🖼️ **Kuvien luokittelija** - Kuvien luokittelu yksityiskohtaisilla kommenteilla
-- 💬 **Tekstin tunnelma** - Analysoi positiivista/negatiivista tekstiä
+- 🌟 **Hei tekoälymaailma** - Ensimmäinen tekoälyohjelmasi (kuviotunnistus)
+- 🧠 **Yksinkertainen neuroverkko** - Rakenna neuroverkko alusta asti
-Nämä esimerkit on suunniteltu auttamaan sinua ymmärtämään tekoälyn käsitteitä ennen kuin sukellat koko opetussuunnitelmaan.
+- 🖼️ **Kuvien luokittelija** - Luokittele kuvia yksityiskohtaisilla kommenteilla
+- 💬 **Tekstin tunnelma** - Analysoi tekstin positiivisuus/negatiivisuus
-### 📚 Koko opetussuunnitelman asennus
+Nämä esimerkit on suunniteltu auttamaan sinua ymmärtämään tekoälyn käsitteitä ennen varsinaisen oppimateriaalin pariin sukeltamista.
-- Olemme luoneet [asennustunnin](./lessons/0-course-setup/setup.md) auttamaan sinua kehitysympäristön perustamisessa. - Opettajille olemme myös luoneet [opetussuunnitelman asennustunnin](./lessons/0-course-setup/for-teachers.md)!
-- Kuinka [ajaa koodi VSCodeissa tai Codespacessa](./lessons/0-course-setup/how-to-run.md)
+### 📚 Koko oppimateriaalin asennus
-Noudata näitä ohjeita:
+- Olemme luoneet [asennustunnin](./lessons/0-course-setup/setup.md) auttamaan sinua kehitysympäristön asennuksessa. - Opettajille olemme luoneet myös [oppimateriaalin asennustunnin](./lessons/0-course-setup/for-teachers.md)!
+- Kuinka [suorittaa koodi VSCode- tai Codespace-ympäristössä](./lessons/0-course-setup/how-to-run.md)
-Forkkaa repositorio: Klikkaa tämän sivun oikeasta yläkulmasta "Fork" -painiketta.
+Noudata näitä vaiheita:
+
+Forkkaa repositorio: Klikkaa sivun oikeasta yläkulmasta "Fork"-painiketta.
Kloonaa repositorio: `git clone https://github.com/microsoft/AI-For-Beginners.git`
-Älä unohda tähdätä (🌟) tätä repoosi helpottaaksesi sen löytymistä myöhemmin.
+Älä unohda tähdittää (🌟) tätä repo:ta, jotta löydät sen helpommin myöhemmin.
-## Tapaa muita oppijoita
+## Tapaa muut oppijat
-Liity viralliseen [AI Discord -palvelimeemme](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) tavata ja verkostoitua kurssin muiden oppijoiden kanssa ja saadaksesi tukea.
+Liity [viralliselle AI Discord -palvelimellemme](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) tavata ja verkostoitua muiden kurssin kävijöiden kanssa sekä saada tukea.
-Jos sinulla on palautetta tuotteesta tai kysymyksiä rakentamisen aikana, käy [Azure AI Foundry Developer Forumissa](https://aka.ms/foundry/forum)
+Jos sinulla on palautetta tuotteesta tai kysymyksiä rakennuksen aikana, käy [Azure AI Foundry Developer Forumissa](https://aka.ms/foundry/forum)
-## Kyselyt
+## Testit
-> **Huomautus kyselyistä**: Kaikki kyselyt löytyvät Quiz-app-kansiosta polusta etc\quiz-app, tai [online tässä](https://ff-quizzes.netlify.app/) Ne ovat linkitettynä tunneissa, kyselysovellusta voi ajaa paikallisesti tai ottaa käyttöön Azure:ssa; noudata ohjeita `quiz-app`-kansiossa. Ne ovat asteittain lokalisoitumassa.
+> **Muistutus testeistä**: Kaikki testit löytyvät Quiz-app-kansiosta sijainnissa etc\quiz-app tai [verkkoversio täällä](https://ff-quizzes.netlify.app/) Testit on linkitetty oppitunneilta; quiz-sovellusta voi ajaa paikallisesti tai ottaa käyttöön Azureen; seuraa `quiz-app`-kansion ohjeita. Testit on vähitellen lokalisoitu.
## Apua kaivataan
-Onko sinulla ehdotuksia tai oletko löytänyt kirjoitus- tai koodivirheitä? Avaa issue tai tee pull request.
+Onko sinulla ehdotuksia tai oletko löytänyt kirjoitus- tai koodivirheitä? Tee issue tai tee pull request.
-## Erityiskiitokset
+## Erityiskiitos
-* **✍️ Päätekijä:** [Dmitry Soshnikov](http://soshnikov.com), tohtori
-* **🔥 Toimittaja:** [Jen Looper](https://twitter.com/jenlooper), tohtori
-* **🎨 Luonnostelija:** [Tomomi Imura](https://twitter.com/girlie_mac)
-* **✅ Kyselyjen tekijä:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
-* **🙏 Ydinosallistujat:** [Evgenii Pishchik](https://github.com/Pe4enIks)
+* **✍️ Pääkirjoittaja:** [Dmitry Soshnikov](http://soshnikov.com), FT
+* **🔥 Toimittaja:** [Jen Looper](https://twitter.com/jenlooper), FT
+* **🎨 Sketchnote-kuvittaja:** [Tomomi Imura](https://twitter.com/girlie_mac)
+* **✅ Testin tekijä:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
+* **🙏 Ydintekijät:** [Evgenii Pishchik](https://github.com/Pe4enIks)
-## Muut opetussuunnitelmat
+## Muut oppimateriaalit
-Tiimimme tuottaa myös muita opetussuunnitelmia! Tutustu:
+Tiimimme tuottaa myös muita oppimateriaaleja! Tutustu:
-### LangChain
-[](https://aka.ms/langchain4j-for-beginners)
-[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
+### LangChain
+[](https://aka.ms/langchain4j-for-beginners)
+[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
---
-### Azure / Edge / MCP / Agentit
-[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
+### Azure / Edge / MCP / Agentit
+[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
---
-
-### Generatiivinen AI -sarja
-[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
-[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
-[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
+
+### Generatiivinen AI -sarja
+[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
+[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
+[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
---
-
-### Perusopetus
-[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
-[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
+
+### Keskeinen oppiminen
+[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
+[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
---
-
-### Copilot-sarja
-[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
+
+### Copilot-sarja
+[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
## Apua saatavilla
-Jos jumitut tai sinulla on kysyttävää tekoälysovellusten rakentamisesta, liity muiden oppijoiden ja kokeneiden kehittäjien keskusteluihin MCP:stä. Se on kiinnostava yhteisö, jossa kysymyksiä saa esittää ja tietoa jaetaan vapaasti.
+Jos jumitut tai sinulla on kysyttävää tekoälysovellusten rakentamisesta, liity muiden oppijoiden ja kokeneiden kehittäjien keskusteluihin MCP:stä. Se on kannustava yhteisö, jossa kysymykset ovat tervetulleita ja tietoa jaetaan vapaasti.
[](https://discord.gg/nTYy5BXMWG)
-Jos sinulla on palautetta tuotteesta tai löytämiesi virheiden vuoksi vieraile:
+Jos sinulla on tuotepalaute tai virheitä rakennusvaiheessa, käy:
[](https://aka.ms/foundry/forum)
---
-**Vastuuvapauslauseke**:
-Tämä asiakirja on käännetty käyttämällä tekoälypohjaista käännöspalvelua [Co-op Translator](https://github.com/Azure/co-op-translator). Vaikka pyrimme tarkkuuteen, ota huomioon, että automaattikäännöksissä voi esiintyä virheitä tai epätarkkuuksia. Asiakirjan alkuperäinen versio alkuperäisellä kielellä on virallinen ja sitova lähde. Tärkeissä asioissa suositellaan ammattilaisen tekemää käännöstä. Emme vastaa mahdollisista väärinymmärryksistä tai tulkinnoista, jotka johtuvat tämän käännöksen käytöstä.
+**Vastuuvapauslauseke**:
+Tämä asiakirja on käännetty tekoälypohjaisella käännöspalvelulla [Co-op Translator](https://github.com/Azure/co-op-translator). Pyrimme tarkkuuteen, mutta automaattiset käännökset saattavat sisältää virheitä tai epätarkkuuksia. Alkuperäinen asiakirja omalla kielellään on virallinen lähde. Tärkeissä asioissa suositellaan ammattilaisen tekemää ihmiskäännöstä. Emme ole vastuussa tästä käännöksestä johtuvista väärinymmärryksistä tai tulkinnoista.
\ No newline at end of file
diff --git a/translations/fi/SECURITY.md b/translations/fi/SECURITY.md
index c1575000..7026e333 100644
--- a/translations/fi/SECURITY.md
+++ b/translations/fi/SECURITY.md
@@ -1,12 +1,3 @@
-
## Tietoturva
Microsoft suhtautuu vakavasti ohjelmistotuotteidensa ja palveluidensa tietoturvaan, mukaan lukien kaikki lähdekoodivarastot, joita hallinnoidaan GitHub-organisaatioidemme kautta, kuten [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin) ja [GitHub-organisaatiomme](https://opensource.microsoft.com/).
diff --git a/translations/fi/etc/CODE_OF_CONDUCT.md b/translations/fi/etc/CODE_OF_CONDUCT.md
index 1502366b..60f4953f 100644
--- a/translations/fi/etc/CODE_OF_CONDUCT.md
+++ b/translations/fi/etc/CODE_OF_CONDUCT.md
@@ -1,12 +1,3 @@
-
# Microsoftin avoimen lähdekoodin toimintasäännöt
Tämä projekti on ottanut käyttöön [Microsoftin avoimen lähdekoodin toimintasäännöt](https://opensource.microsoft.com/codeofconduct/).
diff --git a/translations/fi/etc/CONTRIBUTING.md b/translations/fi/etc/CONTRIBUTING.md
index 68ba1c6d..2dbe087d 100644
--- a/translations/fi/etc/CONTRIBUTING.md
+++ b/translations/fi/etc/CONTRIBUTING.md
@@ -1,12 +1,3 @@
-
# Osallistuminen
Tämä projekti toivottaa tervetulleeksi panoksesi ja ehdotuksesi. Useimmat panokset edellyttävät, että hyväksyt Contributor License Agreementin (CLA), jossa vahvistat, että sinulla on oikeus antaa meille oikeudet käyttää panostasi. Lisätietoja löydät osoitteesta https://cla.microsoft.com.
diff --git a/translations/fi/etc/Mindmap.md b/translations/fi/etc/Mindmap.md
index 10273368..76a16f82 100644
--- a/translations/fi/etc/Mindmap.md
+++ b/translations/fi/etc/Mindmap.md
@@ -1,12 +1,3 @@
-
# AI
## [Johdatus tekoälyyn](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
diff --git a/translations/fi/etc/SUPPORT.md b/translations/fi/etc/SUPPORT.md
index 2807ff92..6819bbe3 100644
--- a/translations/fi/etc/SUPPORT.md
+++ b/translations/fi/etc/SUPPORT.md
@@ -1,12 +1,3 @@
-
# Tuki
## Kuinka raportoida ongelmia ja saada apua
diff --git a/translations/fi/etc/TRANSLATIONS.md b/translations/fi/etc/TRANSLATIONS.md
index d2fa5fbd..7594e3ed 100644
--- a/translations/fi/etc/TRANSLATIONS.md
+++ b/translations/fi/etc/TRANSLATIONS.md
@@ -1,12 +1,3 @@
-
# Osallistu kääntämällä oppitunteja
Toivotamme tervetulleiksi käännökset tämän opetussuunnitelman oppitunneille!
diff --git a/translations/fi/etc/quiz-app/README.md b/translations/fi/etc/quiz-app/README.md
index c3ec73bf..8c670ee7 100644
--- a/translations/fi/etc/quiz-app/README.md
+++ b/translations/fi/etc/quiz-app/README.md
@@ -1,12 +1,3 @@
-
# Visailut
Nämä visailut ovat AI-opetussuunnitelman ennen ja jälkeen luentojen tehtäviä osoitteessa https://aka.ms/ai-beginners
diff --git a/translations/fi/examples/README.md b/translations/fi/examples/README.md
index b7484e3e..ecd3fe40 100644
--- a/translations/fi/examples/README.md
+++ b/translations/fi/examples/README.md
@@ -1,12 +1,3 @@
-
# Aloittelijaystävällisiä AI-esimerkkejä
Tervetuloa! Tämä hakemisto sisältää yksinkertaisia, itsenäisiä esimerkkejä, jotka auttavat sinua pääsemään alkuun tekoälyn ja koneoppimisen parissa. Jokainen esimerkki on suunniteltu aloitteleville käyttäjille, ja niissä on yksityiskohtaiset kommentit sekä vaiheittaiset selitykset.
diff --git a/translations/fi/lessons/0-course-setup/for-teachers.md b/translations/fi/lessons/0-course-setup/for-teachers.md
index 50cbb127..6a918ef7 100644
--- a/translations/fi/lessons/0-course-setup/for-teachers.md
+++ b/translations/fi/lessons/0-course-setup/for-teachers.md
@@ -1,12 +1,3 @@
-
# Opettajille
Haluaisitko käyttää tätä opetusohjelmaa luokassasi? Ole hyvä ja käytä vapaasti!
diff --git a/translations/fi/lessons/0-course-setup/how-to-run.md b/translations/fi/lessons/0-course-setup/how-to-run.md
index 3d238867..f38cf3e6 100644
--- a/translations/fi/lessons/0-course-setup/how-to-run.md
+++ b/translations/fi/lessons/0-course-setup/how-to-run.md
@@ -1,12 +1,3 @@
-
# Kuinka Suorittaa Koodi
Tämä opetussuunnitelma sisältää paljon suoritettavia esimerkkejä ja labroja, joita haluat todennäköisesti suorittaa. Tätä varten sinun on pystyttävä suorittamaan Python-koodia Jupyter-muistikirjoissa, jotka kuuluvat osana tätä opetussuunnitelmaa. Koodin suorittamiseen on useita vaihtoehtoja:
diff --git a/translations/fi/lessons/0-course-setup/setup.md b/translations/fi/lessons/0-course-setup/setup.md
index 581fd85c..40cdbae5 100644
--- a/translations/fi/lessons/0-course-setup/setup.md
+++ b/translations/fi/lessons/0-course-setup/setup.md
@@ -1,12 +1,3 @@
-
# Aloittaminen tämän opintosuunnitelman kanssa
## Oletko opiskelija?
diff --git a/translations/fi/lessons/1-Intro/README.md b/translations/fi/lessons/1-Intro/README.md
index 1dd25e91..c0aa33c4 100644
--- a/translations/fi/lessons/1-Intro/README.md
+++ b/translations/fi/lessons/1-Intro/README.md
@@ -1,12 +1,3 @@
-
# Johdanto tekoälyyn
diff --git a/translations/fi/lessons/1-Intro/assignment.md b/translations/fi/lessons/1-Intro/assignment.md
index 92037865..983c35ec 100644
--- a/translations/fi/lessons/1-Intro/assignment.md
+++ b/translations/fi/lessons/1-Intro/assignment.md
@@ -1,12 +1,3 @@
-
# Pelijamit
Pelit ovat alue, johon tekoälyn ja koneoppimisen kehitys on vaikuttanut merkittävästi. Tässä tehtävässä kirjoita lyhyt essee pelistä, josta pidät ja johon tekoälyn kehitys on vaikuttanut. Pelin tulisi olla tarpeeksi vanha, jotta siihen on voinut vaikuttaa useat erilaiset tietokoneprosessointijärjestelmät. Hyvä esimerkki on shakki tai Go, mutta tutustu myös videopeleihin kuten Pong tai Pac-Man. Kirjoita essee, joka käsittelee pelin menneisyyttä, nykyisyyttä ja tekoälyn tulevaisuutta.
diff --git a/translations/fi/lessons/2-Symbolic/README.md b/translations/fi/lessons/2-Symbolic/README.md
index 05612fc2..af386bbf 100644
--- a/translations/fi/lessons/2-Symbolic/README.md
+++ b/translations/fi/lessons/2-Symbolic/README.md
@@ -1,15 +1,6 @@
-
# Tiedon esittäminen ja asiantuntijajärjestelmät
-
+
> Luonnos [Tomomi Imura](https://twitter.com/girlie_mac)
@@ -41,7 +32,7 @@ Useimmiten emme määrittele tietoa tarkasti, vaan sovitamme sen muihin siihen l
Näin ollen **tiedon esittämisen** ongelmana on löytää jokin tehokas tapa edustaa tietoa tietokoneen sisällä datamuodossa, jotta se olisi automaattisesti hyödynnettävissä. Tätä voidaan tarkastella spektrinä:
-
+
> Kuva: [Dmitry Soshnikov](http://soshnikov.com)
@@ -94,7 +85,7 @@ Lohko-syntaksi | Sisennys | | |
Yksi symbolisen tekoälyn varhaisista menestyksistä olivat ns. **asiantuntijajärjestelmät** – tietokonejärjestelmät, jotka oli suunniteltu toimimaan asiantuntijana rajatussa ongelma-alueessa. Ne perustuivat **tietokantaan**, joka oli kerätty yhdeltä tai useammalta ihmisasiantuntijalta, ja ne sisälsivät **päätöksentekomoottorin**, joka suoritti jonkinlaista päättelyä sen päällä.
- | 
+ | 
---------------------------------------------|------------------------------------------------
Ihmisen hermojärjestelmän yksinkertaistettu rakenne | Tietopohjaisen järjestelmän arkkitehtuuri
@@ -106,7 +97,7 @@ Asiantuntijajärjestelmät rakennetaan kuten ihmisen päättelyjärjestelmä, jo
Esimerkkinä otetaan seuraava asiantuntijajärjestelmä eläimen tunnistamiseen sen fyysisten ominaisuuksien perusteella:
-
+
> Kuva: [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/fi/lessons/2-Symbolic/assignment.md b/translations/fi/lessons/2-Symbolic/assignment.md
index 7f8f3759..0fcb06ff 100644
--- a/translations/fi/lessons/2-Symbolic/assignment.md
+++ b/translations/fi/lessons/2-Symbolic/assignment.md
@@ -1,12 +1,3 @@
-
# Rakenna ontologia
Tietopohjan rakentaminen tarkoittaa mallin luokittelua, joka edustaa faktoja tietystä aiheesta. Valitse aihe - kuten henkilö, paikka tai asia - ja rakenna sitten malli kyseisestä aiheesta. Käytä joitakin tässä oppitunnissa kuvattuja tekniikoita ja mallinrakennusstrategioita. Esimerkkinä voisi olla olohuoneen ontologian luominen, jossa on huonekaluja, valoja ja niin edelleen. Miten olohuone eroaa keittiöstä? Kylpyhuoneesta? Mistä tiedät, että kyseessä on olohuone eikä ruokasali? Käytä [Protégé](https://protege.stanford.edu/) -ohjelmaa ontologiasi rakentamiseen.
diff --git a/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/README.md
index 18e3b6c6..fc2e7555 100644
--- a/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/README.md
+++ b/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/README.md
@@ -1,12 +1,3 @@
-
# Johdanto neuroverkkoihin: Perceptron
## [Ennakkokysely](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@@ -15,7 +6,7 @@ Yksi ensimmäisistä yrityksistä toteuttaa jotain modernin neuroverkon kaltaist
| | |
|--------------|-----------|
-|
| 
|
+|
| 
|
> Kuvat [Wikipedia](https://en.wikipedia.org/wiki/Perceptron)-sivustolta
@@ -34,7 +25,7 @@ y(x) = f(wTx)
missä f on askelaktivointifunktio
-
+
## Perceptronin kouluttaminen
diff --git a/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
index 689d85c9..35ca30f2 100644
--- a/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
+++ b/translations/fi/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
@@ -1,12 +1,3 @@
-
# Moniluokkainen luokittelu perceptronilla
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/README.md
index 600ee2cd..c4d53eac 100644
--- a/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/README.md
+++ b/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/README.md
@@ -1,12 +1,3 @@
-
# Johdanto neuroverkkoihin. Monikerroksinen perceptron
Edellisessä osiossa opit yksinkertaisimmasta neuroverkkonmallista – yksikerroksisesta perceptronista, joka on lineaarinen kahden luokan luokittelumalli.
@@ -65,7 +56,7 @@ Gradienttimenetelmä pysyy samana, mutta gradienttien laskeminen on monimutkaise
Huomaa, että kaikkien näiden lausekkeiden vasemmanpuoleinen osa on sama, ja näin voimme tehokkaasti laskea derivaatat aloittaen tappiofunktiosta ja kulkemalla "taaksepäin" laskentakaavion läpi. Siksi monikerroksisen perceptronin koulutusmenetelmää kutsutaan **takaisinkuljetukseksi** tai 'backpropiksi'.
-
+
> TODO: kuvan lähde
diff --git a/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
index 52d93464..397c61ee 100644
--- a/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
+++ b/translations/fi/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
@@ -1,12 +1,3 @@
-
# MNIST-luokittelu omalla kehikollamme
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/README.md
index 9761e843..cab0b8a1 100644
--- a/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/README.md
+++ b/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/README.md
@@ -1,12 +1,3 @@
-
# Neuroverkkojen Kehykset
Kuten olemme jo oppineet, tehokkaan neuroverkkojen kouluttamisen kannalta meidän täytyy tehdä kaksi asiaa:
diff --git a/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
index 396468dc..7ce92f57 100644
--- a/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
+++ b/translations/fi/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Luokittelu PyTorchilla/TensorFlow'lla
Labraharjoitus [AI for Beginners -opetussuunnitelmasta](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/fi/lessons/3-NeuralNetworks/README.md b/translations/fi/lessons/3-NeuralNetworks/README.md
index 0b652bc6..2f501a9d 100644
--- a/translations/fi/lessons/3-NeuralNetworks/README.md
+++ b/translations/fi/lessons/3-NeuralNetworks/README.md
@@ -1,12 +1,3 @@
-
# Johdanto neuroverkkoihin
diff --git a/translations/fi/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/fi/lessons/4-ComputerVision/06-IntroCV/README.md
index 0a342227..6a24924d 100644
--- a/translations/fi/lessons/4-ComputerVision/06-IntroCV/README.md
+++ b/translations/fi/lessons/4-ComputerVision/06-IntroCV/README.md
@@ -1,12 +1,3 @@
-
# Johdanto tietokonenäköön
[Tietokonenäkö](https://wikipedia.org/wiki/Computer_vision) on tieteenala, jonka tavoitteena on mahdollistaa tietokoneiden saavuttaa korkeatasoinen ymmärrys digitaalisista kuvista. Tämä on varsin laaja määritelmä, sillä *ymmärrys* voi tarkoittaa monia eri asioita, kuten esineen löytämistä kuvasta (**esineentunnistus**), tapahtuman ymmärtämistä (**tapahtumantunnistus**), kuvan kuvailemista tekstillä tai kohtauksen rekonstruointia 3D-muodossa. On myös erityisiä tehtäviä, jotka liittyvät ihmiskuvien käsittelyyn: iän ja tunteiden arviointi, kasvojen tunnistus ja identifiointi sekä 3D-asennon arviointi, muutamia mainitakseni.
@@ -115,7 +106,7 @@ Lue lisää optisesta virtauksesta [tästä erinomaisesta oppaasta](https://lear
Tässä laboratoriossa otat videon, jossa on yksinkertaisia eleitä, ja tavoitteesi on tunnistaa ylös/alas/vasen/oikea-liikkeet optisen virtauksen avulla.
-
+
---
diff --git a/translations/fi/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/fi/lessons/4-ComputerVision/06-IntroCV/lab/README.md
index 44da774a..7df0dc98 100644
--- a/translations/fi/lessons/4-ComputerVision/06-IntroCV/lab/README.md
+++ b/translations/fi/lessons/4-ComputerVision/06-IntroCV/lab/README.md
@@ -1,12 +1,3 @@
-
# Liikkeiden havaitseminen optisella virtausmenetelmällä
Lab-tehtävä [AI for Beginners Curriculum](https://aka.ms/ai-beginners) -materiaalista.
diff --git a/translations/fi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/fi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
index 80caebfd..821670f3 100644
--- a/translations/fi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
+++ b/translations/fi/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
@@ -1,12 +1,3 @@
-
# Tunnetut CNN-arkkitehtuurit
### VGG-16
@@ -25,7 +16,7 @@ Kuten näet, VGG noudattaa perinteistä pyramidirakennetta, joka koostuu konvolu
ResNet on Microsoft Researchin vuonna 2015 ehdottama malliperhe. ResNetin pääidea on käyttää **residuaalilohkoja**:
-
+
> Kuva [tästä artikkelista](https://arxiv.org/pdf/1512.03385.pdf)
@@ -37,7 +28,7 @@ Voit myös ajatella tätä verkkoa kykeneväksi mukauttamaan monimutkaisuutensa
Google Inception -arkkitehtuuri vie tämän idean askeleen pidemmälle ja rakentaa jokaisen verkon kerroksen useiden eri polkujen yhdistelmänä:
-
+
> Kuva [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454) -sivustolta
diff --git a/translations/fi/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/fi/lessons/4-ComputerVision/07-ConvNets/README.md
index 42043818..998e948d 100644
--- a/translations/fi/lessons/4-ComputerVision/07-ConvNets/README.md
+++ b/translations/fi/lessons/4-ComputerVision/07-ConvNets/README.md
@@ -1,12 +1,3 @@
-
# Konvoluutionaaliset neuroverkot
Olemme aiemmin nähneet, että neuroverkot ovat varsin hyviä käsittelemään kuvia, ja jopa yksikerroksinen perceptron pystyy tunnistamaan käsinkirjoitettuja numeroita MNIST-datasta kohtuullisella tarkkuudella. MNIST-datasetti on kuitenkin hyvin erityinen, sillä kaikki numerot on keskitetty kuvan sisälle, mikä tekee tehtävästä yksinkertaisemman.
@@ -24,7 +15,7 @@ Kuvioiden tunnistamiseen käytämme **konvoluutiokertoimia**. Kuten tiedät, kuv
Esimerkiksi, jos sovellamme 3x3 pystysuuntaista ja vaakasuuntaista reunasuodatinta MNIST-numeroihin, voimme saada korostuksia (esim. korkeita arvoja) kohtiin, joissa alkuperäisessä kuvassa on pystysuuntaisia ja vaakasuuntaisia reunoja. Näin ollen näitä kahta suodatinta voidaan käyttää "etsimään" reunoja. Samalla tavalla voimme suunnitella erilaisia suodattimia etsimään muita matalan tason kuvioita:
-
+
> Kuva [Leung-Malik-suodatinpankista](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
diff --git a/translations/fi/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/fi/lessons/4-ComputerVision/07-ConvNets/lab/README.md
index af2c2e96..f3a68f20 100644
--- a/translations/fi/lessons/4-ComputerVision/07-ConvNets/lab/README.md
+++ b/translations/fi/lessons/4-ComputerVision/07-ConvNets/lab/README.md
@@ -1,12 +1,3 @@
-
# Lemmikkien kasvojen luokittelu
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/fi/lessons/4-ComputerVision/08-TransferLearning/README.md
index d81dcfcd..ce1a69be 100644
--- a/translations/fi/lessons/4-ComputerVision/08-TransferLearning/README.md
+++ b/translations/fi/lessons/4-ComputerVision/08-TransferLearning/README.md
@@ -1,12 +1,3 @@
-
# Esikoulutetut verkot ja siirtäminen oppiminen
CNN:ien kouluttaminen voi viedä paljon aikaa, ja siihen tarvitaan runsaasti dataa. Suuri osa ajasta kuluu kuitenkin parhaita matalan tason suodattimia oppiessa, joita verkko voi käyttää kuvioiden tunnistamiseen kuvista. Luonnollinen kysymys herää - voimmeko käyttää yhdellä datasetillä koulutettua neuroverkkoa ja mukauttaa sen luokittelemaan erilaisia kuvia ilman täydellistä koulutusprosessia?
diff --git a/translations/fi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/fi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
index 7269b8fb..b611404e 100644
--- a/translations/fi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
+++ b/translations/fi/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
@@ -1,12 +1,3 @@
-
# Syväoppimisen koulutusvinkit
Kun neuroverkot syvenevät, niiden koulutusprosessi muuttuu yhä haastavammaksi. Yksi merkittävä ongelma on niin sanottu [häviävät gradientit](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) tai [räjähtävät gradientit](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Tämä artikkeli](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) tarjoaa hyvän johdannon näihin ongelmiin.
diff --git a/translations/fi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/fi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
index a07c290b..a97003be 100644
--- a/translations/fi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
+++ b/translations/fi/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
@@ -1,12 +1,3 @@
-
# Oxfordin lemmikkien luokittelu siirtämällä oppimista hyödyntäen
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/fi/lessons/4-ComputerVision/09-Autoencoders/README.md
index a2356fa6..ddb2de25 100644
--- a/translations/fi/lessons/4-ComputerVision/09-Autoencoders/README.md
+++ b/translations/fi/lessons/4-ComputerVision/09-Autoencoders/README.md
@@ -1,12 +1,3 @@
-
# Autokooderit
Kun koulutetaan CNN-verkkoja, yksi ongelmista on, että tarvitsemme paljon merkittyä dataa. Kuvien luokittelussa meidän täytyy jakaa kuvat eri luokkiin, mikä vaatii manuaalista työtä.
@@ -46,7 +37,7 @@ Yhteenveto:
* Otamme näytteen `sample` jakaumasta N(zmean,exp(zlog\_sigma))
* Dekooderi yrittää dekoodata alkuperäisen kuvan käyttäen `sample`-vektoria syötteenä
- 
+ 
> Kuva [tästä blogikirjoituksesta](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) kirjoittanut Isaak Dykeman
@@ -57,13 +48,13 @@ Variatiiviset autokooderit käyttävät monimutkaista häviöfunktiota, joka koo
Yksi tärkeä etu VAE:ssa on, että niiden avulla voidaan luoda uusia kuvia suhteellisen helposti, koska tiedämme, mistä jakaumasta voimme ottaa näytteitä latenttivektoreille. Esimerkiksi, jos koulutamme VAE:n 2D-latenttivektorilla MNIST-datasetilla, voimme sitten muuttaa latenttivektorin komponentteja saadaksemme eri numeroita:
-
+
> Kuva [Dmitry Soshnikovilta](http://soshnikov.com)
Huomaa, kuinka kuvat sulautuvat toisiinsa, kun alamme saada latenttivektoreita eri osista latenttiparametritilaa. Voimme myös visualisoida tämän tilan 2D-muodossa:
-
+
> Kuva [Dmitry Soshnikovilta](http://soshnikov.com)
diff --git a/translations/fi/lessons/4-ComputerVision/10-GANs/README.md b/translations/fi/lessons/4-ComputerVision/10-GANs/README.md
index 4b9f7299..9cc18ccf 100644
--- a/translations/fi/lessons/4-ComputerVision/10-GANs/README.md
+++ b/translations/fi/lessons/4-ComputerVision/10-GANs/README.md
@@ -1,12 +1,3 @@
-
# Generatiiviset vastakkaiset verkot
Edellisessä osiossa opimme **generatiivisista malleista**: malleista, jotka voivat luoda uusia kuvia, jotka muistuttavat koulutusdatan kuvia. VAE oli hyvä esimerkki generatiivisesta mallista.
@@ -17,7 +8,7 @@ Kuitenkin, jos yritämme luoda jotain todella merkityksellistä, kuten maalaukse
GANin pääidea on käyttää kahta neuroverkkoa, jotka koulutetaan toisiaan vastaan:
-
+
> Kuva: [Dmitry Soshnikov](http://soshnikov.com)
@@ -41,7 +32,7 @@ Generaattori on hieman monimutkaisempi. Voit ajatella sen olevan käänteinen di
> ✅ Koska konvoluutiokerros toteutetaan lineaarisena suodattimena, joka kulkee kuvan läpi, dekonvoluutio on pohjimmiltaan samanlainen kuin konvoluutio ja voidaan toteuttaa samalla kerroslogiikalla.
-
+
> Kuva: [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/README.md
index aaeeb356..99b50b80 100644
--- a/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/README.md
+++ b/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/README.md
@@ -1,12 +1,3 @@
-
# Objektien tunnistus
Kuvien luokittelumallit, joita olemme tähän mennessä käsitelleet, ottavat kuvan ja tuottavat kategorisen tuloksen, kuten luokan 'numero' MNIST-ongelmassa. Monissa tapauksissa emme kuitenkaan halua vain tietää, että kuva esittää objekteja – haluamme pystyä määrittämään niiden tarkka sijainti. Juuri tähän **objektien tunnistus** keskittyy.
diff --git a/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
index a396245e..becb64c4 100644
--- a/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
+++ b/translations/fi/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
@@ -1,12 +1,3 @@
-
# Pään tunnistus Hollywood Heads -datastolla
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/fi/lessons/4-ComputerVision/12-Segmentation/README.md
index 501b7179..661aaabc 100644
--- a/translations/fi/lessons/4-ComputerVision/12-Segmentation/README.md
+++ b/translations/fi/lessons/4-ComputerVision/12-Segmentation/README.md
@@ -1,12 +1,3 @@
-
# Segmentointi
Olemme aiemmin oppineet objektien tunnistamisesta, joka mahdollistaa objektien paikantamisen kuvassa ennustamalla niiden *rajauslaatikot*. Joissakin tehtävissä emme kuitenkaan tarvitse pelkästään rajauslaatikoita, vaan myös tarkempaa objektien paikantamista. Tätä tehtävää kutsutaan **segmentoinniksi**.
@@ -20,7 +11,7 @@ Segmentointi voidaan nähdä **pikseliluokitteluna**, jossa jokaiselle kuvan pik
Esimerkiksi instanssisegmentoinnissa nämä lampaat ovat eri objekteja, mutta semanttisessa segmentoinnissa kaikki lampaat kuuluvat yhteen luokkaan.
-
+
> Kuva [tästä blogikirjoituksesta](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)
@@ -29,7 +20,7 @@ Segmentointiin on olemassa erilaisia neuroverkkoarkkitehtuureja, mutta niillä k
* **Kooderi** (Encoder) poimii piirteitä syötekuvasta.
* **Dekooderi** (Decoder) muuntaa nämä piirteet **maskikuvaksi**, jonka koko ja kanavien määrä vastaavat luokkien määrää.
-
+
> Kuva [tästä julkaisusta](https://arxiv.org/pdf/2001.05566.pdf)
@@ -43,7 +34,7 @@ Tässä oppitunnissa näemme segmentoinnin käytännössä kouluttamalla verkkoa
> ✅ Tämä tekniikka sopii erityisen hyvin tämän tyyppiseen lääketieteelliseen kuvantamiseen, mutta mitä muita tosielämän sovelluksia voisit kuvitella?
-
+
> Kuva PH2-tietokannasta
diff --git a/translations/fi/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/fi/lessons/4-ComputerVision/12-Segmentation/lab/README.md
index fb2162c5..238bcc69 100644
--- a/translations/fi/lessons/4-ComputerVision/12-Segmentation/lab/README.md
+++ b/translations/fi/lessons/4-ComputerVision/12-Segmentation/lab/README.md
@@ -1,12 +1,3 @@
-
# Ihmiskehon segmentointi
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/4-ComputerVision/README.md b/translations/fi/lessons/4-ComputerVision/README.md
index 49d4a363..bbb38937 100644
--- a/translations/fi/lessons/4-ComputerVision/README.md
+++ b/translations/fi/lessons/4-ComputerVision/README.md
@@ -1,12 +1,3 @@
-
# Tietokonenäkö
diff --git a/translations/fi/lessons/5-NLP/13-TextRep/README.md b/translations/fi/lessons/5-NLP/13-TextRep/README.md
index c9b79ca2..e5be9140 100644
--- a/translations/fi/lessons/5-NLP/13-TextRep/README.md
+++ b/translations/fi/lessons/5-NLP/13-TextRep/README.md
@@ -1,12 +1,3 @@
-
# Tekstin esittäminen tensoreina
## [Ennakkokysely](https://ff-quizzes.netlify.app/en/ai/quiz/25)
@@ -25,7 +16,7 @@ Tavoitteenamme on luokitella uutinen yhteen kategorioista tekstin perusteella.
Jos haluamme ratkaista luonnollisen kielen käsittelyn (NLP) tehtäviä neuroverkoilla, meidän täytyy löytää tapa esittää teksti tensoreina. Tietokoneet esittävät tekstimerkit jo numeroina, jotka vastaavat näytöllä näkyviä fontteja, käyttäen esimerkiksi ASCII- tai UTF-8-koodauksia.
-
+
> [Kuvan lähde](https://www.seobility.net/en/wiki/ASCII)
@@ -48,7 +39,7 @@ Joissakin tapauksissa voimme harkita tri-grammien - kolmen sanan yhdistelmien -
Kun ratkaistaan tehtäviä, kuten tekstin luokittelua, meidän täytyy pystyä esittämään teksti yhdellä kiinteän kokoisella vektorilla, jota käytämme syötteenä lopulliselle tiheälle luokittelijalle. Yksi yksinkertaisimmista tavoista tehdä tämä on yhdistää kaikki yksittäiset sanan esitykset, esimerkiksi lisäämällä ne yhteen. Jos lisäämme jokaisen sanan one-hot-koodaukset, päädymme frekvenssivektoriin, joka näyttää, kuinka monta kertaa kukin sana esiintyy tekstissä. Tällainen tekstin esitys kutsutaan **bag-of-words** (BoW).
-
+
> Kuva: kirjoittaja
diff --git a/translations/fi/lessons/5-NLP/13-TextRep/assignment.md b/translations/fi/lessons/5-NLP/13-TextRep/assignment.md
index 5311dc05..3cca8f1a 100644
--- a/translations/fi/lessons/5-NLP/13-TextRep/assignment.md
+++ b/translations/fi/lessons/5-NLP/13-TextRep/assignment.md
@@ -1,12 +1,3 @@
-
# Tehtävä: Muistikirjat
Käytä tämän oppitunnin muistikirjoja (joko PyTorch- tai TensorFlow-versiota) ja suorita ne uudelleen käyttäen omaa datasettiäsi, esimerkiksi Kagglesta löytyvää, ja muista mainita lähde. Muokkaa muistikirjaa korostaaksesi omia havaintojasi. Kokeile joitakin innovatiivisia datasettejä, jotka saattavat olla yllättäviä, kuten [tämä UFO-havaintoja käsittelevä datasetti](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) NUFORC:lta.
diff --git a/translations/fi/lessons/5-NLP/14-Embeddings/README.md b/translations/fi/lessons/5-NLP/14-Embeddings/README.md
index dc222659..6f256cde 100644
--- a/translations/fi/lessons/5-NLP/14-Embeddings/README.md
+++ b/translations/fi/lessons/5-NLP/14-Embeddings/README.md
@@ -1,12 +1,3 @@
-
# Upotukset
## [Ennakkokysely](https://ff-quizzes.netlify.app/en/ai/quiz/27)
diff --git a/translations/fi/lessons/5-NLP/14-Embeddings/assignment.md b/translations/fi/lessons/5-NLP/14-Embeddings/assignment.md
index 7a3f3446..06d742b5 100644
--- a/translations/fi/lessons/5-NLP/14-Embeddings/assignment.md
+++ b/translations/fi/lessons/5-NLP/14-Embeddings/assignment.md
@@ -1,12 +1,3 @@
-
# Tehtävä: Muistikirjat
Käytä tämän oppitunnin muistikirjoja (joko PyTorch- tai TensorFlow-versiota) ja suorita ne uudelleen käyttäen omaa datasettiäsi, esimerkiksi Kagglesta löytyvää, ja muista mainita lähde. Muokkaa muistikirjaa korostaaksesi omia havaintojasi. Kokeile erilaista datasettiä ja dokumentoi havaintosi, käyttäen esimerkiksi tekstiä kuten [nämä Beatlesin laulujen sanat](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics).
diff --git a/translations/fi/lessons/5-NLP/15-LanguageModeling/README.md b/translations/fi/lessons/5-NLP/15-LanguageModeling/README.md
index 0ef02353..feb7b60f 100644
--- a/translations/fi/lessons/5-NLP/15-LanguageModeling/README.md
+++ b/translations/fi/lessons/5-NLP/15-LanguageModeling/README.md
@@ -1,12 +1,3 @@
-
# Kielen mallintaminen
Semanttiset upotukset, kuten Word2Vec ja GloVe, ovat itse asiassa ensimmäinen askel kohti **kielen mallintamista** - mallien luomista, jotka jollain tavalla *ymmärtävät* (tai *edustavat*) kielen luonnetta.
diff --git a/translations/fi/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/fi/lessons/5-NLP/15-LanguageModeling/lab/README.md
index 81d72171..9c91bf5c 100644
--- a/translations/fi/lessons/5-NLP/15-LanguageModeling/lab/README.md
+++ b/translations/fi/lessons/5-NLP/15-LanguageModeling/lab/README.md
@@ -1,12 +1,3 @@
-
# Skip-Gram-mallin kouluttaminen
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/5-NLP/16-RNN/README.md b/translations/fi/lessons/5-NLP/16-RNN/README.md
index 6f52a3b9..ea5d2bfc 100644
--- a/translations/fi/lessons/5-NLP/16-RNN/README.md
+++ b/translations/fi/lessons/5-NLP/16-RNN/README.md
@@ -1,12 +1,3 @@
-
# Toistuvat Neuronaaliverkot
## [Ennakkokysely](https://ff-quizzes.netlify.app/en/ai/quiz/31)
@@ -31,7 +22,7 @@ Katsotaan, miten yksinkertainen RNN-solu on järjestetty. Se ottaa syötteenä e
Yksinkertaisessa RNN-solussa on kaksi painomatriisia: yksi muuntaa syötesymbolin (kutsutaan sitä W:ksi) ja toinen muuntaa syötetilan (H). Tässä tapauksessa verkon ulostulo lasketaan kaavalla σ(W×Xi+H×Si-1+b), missä σ on aktivointifunktio ja b on lisäbias.
-
+
> Kuva: kirjoittaja
diff --git a/translations/fi/lessons/5-NLP/16-RNN/assignment.md b/translations/fi/lessons/5-NLP/16-RNN/assignment.md
index b402c03b..3a5ce121 100644
--- a/translations/fi/lessons/5-NLP/16-RNN/assignment.md
+++ b/translations/fi/lessons/5-NLP/16-RNN/assignment.md
@@ -1,12 +1,3 @@
-
# Tehtävä: Muistikirjat
Käytä tämän oppitunnin mukana olevia muistikirjoja (joko PyTorch- tai TensorFlow-versiota) ja suorita ne uudelleen käyttäen omaa datasettiäsi, esimerkiksi Kagglesta, ja muista mainita lähde. Muokkaa muistikirjaa korostaaksesi omia havaintojasi. Kokeile erilaista datasettiä ja dokumentoi havaintosi, käyttäen tekstiä kuten [tämä Kaggle-kilpailudata sääaiheisista twiiteistä](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv).
diff --git a/translations/fi/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/fi/lessons/5-NLP/17-GenerativeNetworks/README.md
index 43e2738c..c7065220 100644
--- a/translations/fi/lessons/5-NLP/17-GenerativeNetworks/README.md
+++ b/translations/fi/lessons/5-NLP/17-GenerativeNetworks/README.md
@@ -1,12 +1,3 @@
-
# Generatiiviset verkot
## [Ennakkokysely](https://ff-quizzes.netlify.app/en/ai/quiz/33)
@@ -36,7 +27,7 @@ Koulutamme tämän RNN:n tuottamaan tekstiä askel askeleelta. Jokaisessa vaihee
Kun tuotamme tekstiä (inferenssin aikana), aloitamme jollain **aloitustekstillä**, joka syötetään RNN-soluihin tuottamaan sen välimuistin, ja sitten tästä tilasta alkaa generointi. Tuotamme yhden merkin kerrallaan ja syötämme tilan ja tuotetun merkin seuraavaan RNN-soluun tuottamaan seuraavan, kunnes olemme tuottaneet tarpeeksi merkkejä.
-
+
> Kuva kirjoittajalta
diff --git a/translations/fi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/fi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
index a132db58..793abfd5 100644
--- a/translations/fi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
+++ b/translations/fi/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Sanatason tekstin generointi RNN:ien avulla
Laboraatiotehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/5-NLP/18-Transformers/README.md b/translations/fi/lessons/5-NLP/18-Transformers/README.md
index a67fa3a7..56e3f27f 100644
--- a/translations/fi/lessons/5-NLP/18-Transformers/README.md
+++ b/translations/fi/lessons/5-NLP/18-Transformers/README.md
@@ -1,12 +1,3 @@
-
# Huomiomekanismit ja Transformerit
## [Ennakkokysely](https://ff-quizzes.netlify.app/en/ai/quiz/35)
@@ -56,7 +47,7 @@ Positionaalisen koodauksen idea on seuraava.
* Koulutettava upotus, kuten token-upotus. Tämä on lähestymistapa, jota tarkastelemme tässä. Sovellamme upotuskerroksia sekä tokeneihin että niiden sijainteihin, jolloin saadaan samankokoiset upotusvektorit, jotka sitten lisätään yhteen.
* Kiinteä positionaalinen koodausfunktio, kuten alkuperäisessä paperissa ehdotettiin.
-
+
> Kuva kirjoittajalta
diff --git a/translations/fi/lessons/5-NLP/18-Transformers/assignment.md b/translations/fi/lessons/5-NLP/18-Transformers/assignment.md
index c1959d84..6de621b3 100644
--- a/translations/fi/lessons/5-NLP/18-Transformers/assignment.md
+++ b/translations/fi/lessons/5-NLP/18-Transformers/assignment.md
@@ -1,12 +1,3 @@
-
# Tehtävä: Transformers
Kokeile Transformers-kirjastoa HuggingFacessa! Testaa joitakin heidän tarjoamiaan skriptejä, joilla voit työskennellä heidän sivustollaan saatavilla olevien mallien kanssa: https://huggingface.co/docs/transformers/run_scripts. Kokeile jotakin heidän datakokonaisuuksistaan, tuo sitten yksi omista datakokonaisuuksistasi tästä kurssista tai Kagglesta ja katso, voitko luoda mielenkiintoisia tekstejä. Laadi muistikirja havainnoistasi.
diff --git a/translations/fi/lessons/5-NLP/19-NER/README.md b/translations/fi/lessons/5-NLP/19-NER/README.md
index e8a39109..90139434 100644
--- a/translations/fi/lessons/5-NLP/19-NER/README.md
+++ b/translations/fi/lessons/5-NLP/19-NER/README.md
@@ -1,12 +1,3 @@
-
# Nimien tunnistus (Named Entity Recognition)
Tähän mennessä olemme keskittyneet pääasiassa yhteen NLP-tehtävään - luokitteluun. On kuitenkin olemassa myös muita NLP-tehtäviä, joita voidaan toteuttaa neuroverkoilla. Yksi näistä tehtävistä on **[nimien tunnistus](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), joka keskittyy tunnistamaan tekstistä tiettyjä entiteettejä, kuten paikkoja, henkilön nimiä, päivämäärä- ja aikavälejä, kemiallisia kaavoja ja niin edelleen.
@@ -17,7 +8,7 @@ Tähän mennessä olemme keskittyneet pääasiassa yhteen NLP-tehtävään - luo
Oletetaan, että haluat kehittää luonnollisen kielen chatbotin, joka on samanlainen kuin Amazon Alexa tai Google Assistant. Älykkäät chatbotit toimivat *ymmärtämällä* käyttäjän tarpeet tekemällä tekstiluokittelua syötteenä annettuun lauseeseen. Tämän luokittelun tuloksena saadaan niin sanottu **intentio**, joka määrittää, mitä chatbotin tulisi tehdä.
-
+
> Kuva: kirjoittaja
diff --git a/translations/fi/lessons/5-NLP/19-NER/lab/README.md b/translations/fi/lessons/5-NLP/19-NER/lab/README.md
index 61fbe088..a9d8e4ec 100644
--- a/translations/fi/lessons/5-NLP/19-NER/lab/README.md
+++ b/translations/fi/lessons/5-NLP/19-NER/lab/README.md
@@ -1,12 +1,3 @@
-
# NER
Lab-tehtävä [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners) -materiaalista.
diff --git a/translations/fi/lessons/5-NLP/20-LangModels/README.md b/translations/fi/lessons/5-NLP/20-LangModels/README.md
index 7f838722..ab80a20a 100644
--- a/translations/fi/lessons/5-NLP/20-LangModels/README.md
+++ b/translations/fi/lessons/5-NLP/20-LangModels/README.md
@@ -1,12 +1,3 @@
-
# Esikoulutetut Suuret Kielenmallit
Kaikissa aiemmissa tehtävissämme olemme kouluttaneet neuroverkkoa suorittamaan tietyn tehtävän käyttäen merkittyä aineistoa. Suurten transformer-mallien, kuten BERT:n, kohdalla käytämme kielenmallinnusta itseohjautuvassa muodossa rakentaaksemme kielenmallin, joka sitten erikoistetaan tiettyyn jatkotehtävään lisäkoulutuksella, joka keskittyy tiettyyn alaan. On kuitenkin osoitettu, että suuret kielenmallit voivat ratkaista monia tehtäviä myös ilman mitään alakohtaista koulutusta. Malliperhe, joka pystyy tähän, tunnetaan nimellä **GPT**: Generative Pre-Trained Transformer.
diff --git a/translations/fi/lessons/5-NLP/README.md b/translations/fi/lessons/5-NLP/README.md
index 57f7e776..0e41b28d 100644
--- a/translations/fi/lessons/5-NLP/README.md
+++ b/translations/fi/lessons/5-NLP/README.md
@@ -1,12 +1,3 @@
-
# Luonnollisen kielen käsittely
diff --git a/translations/fi/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/fi/lessons/6-Other/21-GeneticAlgorithms/README.md
index 9b63d953..0645ac0b 100644
--- a/translations/fi/lessons/6-Other/21-GeneticAlgorithms/README.md
+++ b/translations/fi/lessons/6-Other/21-GeneticAlgorithms/README.md
@@ -1,12 +1,3 @@
-
# Geneettiset algoritmit
## [Esiluentakysely](https://ff-quizzes.netlify.app/en/ai/quiz/41)
diff --git a/translations/fi/lessons/6-Other/22-DeepRL/README.md b/translations/fi/lessons/6-Other/22-DeepRL/README.md
index 959a6519..29a99db6 100644
--- a/translations/fi/lessons/6-Other/22-DeepRL/README.md
+++ b/translations/fi/lessons/6-Other/22-DeepRL/README.md
@@ -1,12 +1,3 @@
-
# Syvävahvistusoppiminen
Vahvistusoppiminen (RL) nähdään yhtenä koneoppimisen perusparadigmoista, yhdessä ohjatun oppimisen ja ohjaamattoman oppimisen kanssa. Siinä missä ohjatussa oppimisessa tukeudumme tunnettuja tuloksia sisältävään aineistoon, RL perustuu **oppimiseen tekemällä**. Esimerkiksi, kun näemme ensimmäistä kertaa tietokonepelin, alamme pelata sitä, vaikka emme tiedä sääntöjä, ja pian pystymme parantamaan taitojamme pelkästään pelaamalla ja mukauttamalla käyttäytymistämme.
@@ -34,7 +25,7 @@ Olette varmasti nähneet moderneja tasapainolaitteita, kuten *Segway* tai *Gyros
Yksinkertaistettu versio tasapainottamisesta tunnetaan nimellä **CartPole-ongelma**. CartPole-maailmassa meillä on vaakasuuntainen liukusäädin, joka voi liikkua vasemmalle tai oikealle, ja tavoitteena on tasapainottaa pystysuora tanko liukusäätimen päällä sen liikkuessa.
-
+
Tämän ympäristön luomiseen ja käyttämiseen tarvitsemme muutaman rivin Python-koodia:
diff --git a/translations/fi/lessons/6-Other/22-DeepRL/lab/README.md b/translations/fi/lessons/6-Other/22-DeepRL/lab/README.md
index 3946ae52..4c11b951 100644
--- a/translations/fi/lessons/6-Other/22-DeepRL/lab/README.md
+++ b/translations/fi/lessons/6-Other/22-DeepRL/lab/README.md
@@ -1,12 +1,3 @@
-
## Ympäristö
Mountain Car -ympäristö koostuu autosta, joka on jumissa laaksossa. Tavoitteesi on hypätä ulos laaksosta ja saavuttaa lippu. Voit suorittaa seuraavat toiminnot: kiihdyttää vasemmalle, kiihdyttää oikealle tai olla tekemättä mitään. Voit havainnoida auton sijaintia x-akselilla ja sen nopeutta.
diff --git a/translations/fi/lessons/6-Other/23-MultiagentSystems/README.md b/translations/fi/lessons/6-Other/23-MultiagentSystems/README.md
index 7cb6e095..d68c4cba 100644
--- a/translations/fi/lessons/6-Other/23-MultiagentSystems/README.md
+++ b/translations/fi/lessons/6-Other/23-MultiagentSystems/README.md
@@ -1,12 +1,3 @@
-
# Multi-agenttijärjestelmät
Yksi mahdollinen tapa saavuttaa älykkyyttä on niin sanottu **emergentti** (tai **synergeettinen**) lähestymistapa, joka perustuu siihen, että monien suhteellisen yksinkertaisten agenttien yhdistetty käyttäytyminen voi johtaa järjestelmän kokonaisvaltaisesti monimutkaisempaan (tai älykkäämpään) käyttäytymiseen. Teoreettisesti tämä perustuu [kollektiivisen älykkyyden](https://en.wikipedia.org/wiki/Collective_intelligence), [emergentismin](https://en.wikipedia.org/wiki/Global_brain) ja [evolutionaarisen kybernetiikan](https://en.wikipedia.org/wiki/Global_brain) periaatteisiin, jotka väittävät, että korkeamman tason järjestelmät saavat jonkinlaista lisäarvoa, kun ne yhdistetään asianmukaisesti alemman tason järjestelmistä (niin sanottu *metajärjestelmäsiirtymän periaate*).
@@ -60,7 +51,7 @@ Voit [ladata](https://ccl.northwestern.edu/netlogo/download.shtml) ja asentaa Ne
NetLogon hienous on siinä, että se sisältää kirjaston toimivia malleja, joita voit kokeilla. Siirry **File → Models Library**, ja sinulla on monia mallikategorioita, joista valita.
-
+
> Kuvakaappaus mallikirjastosta Dmitry Soshnikovilta
diff --git a/translations/fi/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/fi/lessons/6-Other/23-MultiagentSystems/assignment.md
index 3ec114e2..6dc6f139 100644
--- a/translations/fi/lessons/6-Other/23-MultiagentSystems/assignment.md
+++ b/translations/fi/lessons/6-Other/23-MultiagentSystems/assignment.md
@@ -1,12 +1,3 @@
-
# NetLogo-tehtävä
Valitse yksi NetLogon kirjaston malleista ja käytä sitä simuloimaan todellista tilannetta mahdollisimman tarkasti. Hyvä esimerkki olisi muokata Virus-mallia Alternative Visualizations -kansiossa, jotta se näyttää, miten sitä voidaan käyttää COVID-19:n leviämisen mallintamiseen. Voitko rakentaa mallin, joka jäljittelee todellisen viruksen leviämistä?
diff --git a/translations/fi/lessons/7-Ethics/README.md b/translations/fi/lessons/7-Ethics/README.md
index 026afe64..ca0bfb44 100644
--- a/translations/fi/lessons/7-Ethics/README.md
+++ b/translations/fi/lessons/7-Ethics/README.md
@@ -1,12 +1,3 @@
-
# Eettinen ja vastuullinen tekoäly
Olet melkein suorittanut tämän kurssin, ja toivon, että tähän mennessä näet selvästi, että tekoäly perustuu useisiin muodollisiin matemaattisiin menetelmiin, jotka mahdollistavat suhteiden löytämisen datasta ja mallien kouluttamisen jäljittelemään joitakin ihmisen käyttäytymisen piirteitä. Tässä historian vaiheessa pidämme tekoälyä erittäin voimakkaana työkaluna, joka auttaa meitä löytämään kaavoja datasta ja soveltamaan niitä uusien ongelmien ratkaisemiseen.
diff --git a/translations/fi/lessons/README.md b/translations/fi/lessons/README.md
index 082dffc8..2fc87274 100644
--- a/translations/fi/lessons/README.md
+++ b/translations/fi/lessons/README.md
@@ -1,12 +1,3 @@
-
# Yleiskatsaus
diff --git a/translations/fi/lessons/X-Extras/X1-MultiModal/README.md b/translations/fi/lessons/X-Extras/X1-MultiModal/README.md
index 71ee4781..43a4a169 100644
--- a/translations/fi/lessons/X-Extras/X1-MultiModal/README.md
+++ b/translations/fi/lessons/X-Extras/X1-MultiModal/README.md
@@ -1,12 +1,3 @@
-
# Monimodaaliset verkot
Transformer-mallien menestyksen jälkeen NLP-tehtävissä samoja tai samankaltaisia arkkitehtuureja on alettu soveltaa myös tietokonenäkötehtäviin. Kasvava kiinnostus kohdistuu mallien rakentamiseen, jotka *yhdistävät* näkö- ja luonnollisen kielen käsittelyn kyvyt. Yksi tällainen yritys on OpenAI:n kehittämä CLIP ja DALL.E.
diff --git a/translations/fi/lessons/sketchnotes/LICENSE.md b/translations/fi/lessons/sketchnotes/LICENSE.md
index b0081022..37d4d1e3 100644
--- a/translations/fi/lessons/sketchnotes/LICENSE.md
+++ b/translations/fi/lessons/sketchnotes/LICENSE.md
@@ -1,12 +1,3 @@
-
Oikeudet, tämä Public License koskee sinua;
c. et voi tarjota tai asettaa lisäehtoja tai -rajoituksia, tai soveltaa tehokkaita teknologisia toimenpiteitä, jotka rajoittavat oikeuksien käyttöä, jotka on myönnetty tämän Public License -lisenssin nojalla.
diff --git a/translations/fi/lessons/sketchnotes/README.md b/translations/fi/lessons/sketchnotes/README.md
index 1bfb61c8..233c63ba 100644
--- a/translations/fi/lessons/sketchnotes/README.md
+++ b/translations/fi/lessons/sketchnotes/README.md
@@ -1,12 +1,3 @@
-
Kaikki opetussuunnitelman sketchnotet voi ladata täältä.
🎨 Luonut: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))
diff --git a/translations/fi/troubleshoot.md b/translations/fi/troubleshoot.md
index de31b4f7..048dd1c9 100644
--- a/translations/fi/troubleshoot.md
+++ b/translations/fi/troubleshoot.md
@@ -1,12 +1,3 @@
-
# AI-For-Beginners Vianmääritysopas
Tämä opas auttaa ratkaisemaan yleisiä ongelmia, joita voi kohdata käyttäessäsi tai osallistuessasi [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners) -repositoryyn. Jokainen ongelma sisältää taustatietoa, oireet, selitykset ja vaiheittaiset ratkaisut.
diff --git a/translations/nl/.co-op-translator.json b/translations/nl/.co-op-translator.json
new file mode 100644
index 00000000..0e7dd818
--- /dev/null
+++ b/translations/nl/.co-op-translator.json
@@ -0,0 +1,398 @@
+{
+ "AGENTS.md": {
+ "original_hash": "6b11a37115944252ab3ed04e358d830d",
+ "translation_date": "2025-10-03T09:24:27+00:00",
+ "source_file": "AGENTS.md",
+ "language_code": "nl"
+ },
+ "README.md": {
+ "original_hash": "1984fc89dd304a8a33ab5584691a99aa",
+ "translation_date": "2026-01-30T02:07:23+00:00",
+ "source_file": "README.md",
+ "language_code": "nl"
+ },
+ "SECURITY.md": {
+ "original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
+ "translation_date": "2025-08-28T19:13:31+00:00",
+ "source_file": "SECURITY.md",
+ "language_code": "nl"
+ },
+ "etc/CODE_OF_CONDUCT.md": {
+ "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
+ "translation_date": "2025-08-28T20:13:26+00:00",
+ "source_file": "etc/CODE_OF_CONDUCT.md",
+ "language_code": "nl"
+ },
+ "etc/CONTRIBUTING.md": {
+ "original_hash": "847a587aa1b83f4d00858183ff3ed18a",
+ "translation_date": "2025-08-28T20:13:02+00:00",
+ "source_file": "etc/CONTRIBUTING.md",
+ "language_code": "nl"
+ },
+ "etc/Mindmap.md": {
+ "original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
+ "translation_date": "2025-08-28T20:11:05+00:00",
+ "source_file": "etc/Mindmap.md",
+ "language_code": "nl"
+ },
+ "etc/SUPPORT.md": {
+ "original_hash": "fdfc08baee91e402938a2b1f94fe0949",
+ "translation_date": "2025-08-28T20:10:08+00:00",
+ "source_file": "etc/SUPPORT.md",
+ "language_code": "nl"
+ },
+ "etc/TRANSLATIONS.md": {
+ "original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
+ "translation_date": "2025-08-28T20:12:34+00:00",
+ "source_file": "etc/TRANSLATIONS.md",
+ "language_code": "nl"
+ },
+ "etc/quiz-app/README.md": {
+ "original_hash": "d699cf8509f74baa5b0b838de5cf0662",
+ "translation_date": "2025-08-28T20:13:53+00:00",
+ "source_file": "etc/quiz-app/README.md",
+ "language_code": "nl"
+ },
+ "examples/README.md": {
+ "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
+ "translation_date": "2025-10-03T11:32:01+00:00",
+ "source_file": "examples/README.md",
+ "language_code": "nl"
+ },
+ "lessons/0-course-setup/for-teachers.md": {
+ "original_hash": "a094ef9927883de1cfcee51dbd143381",
+ "translation_date": "2025-08-28T19:19:04+00:00",
+ "source_file": "lessons/0-course-setup/for-teachers.md",
+ "language_code": "nl"
+ },
+ "lessons/0-course-setup/how-to-run.md": {
+ "original_hash": "a4717bd9103b9f6cd84d534b83534689",
+ "translation_date": "2026-01-16T03:04:55+00:00",
+ "source_file": "lessons/0-course-setup/how-to-run.md",
+ "language_code": "nl"
+ },
+ "lessons/0-course-setup/setup.md": {
+ "original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
+ "translation_date": "2025-12-12T19:56:46+00:00",
+ "source_file": "lessons/0-course-setup/setup.md",
+ "language_code": "nl"
+ },
+ "lessons/1-Intro/README.md": {
+ "original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
+ "translation_date": "2025-11-18T21:41:38+00:00",
+ "source_file": "lessons/1-Intro/README.md",
+ "language_code": "nl"
+ },
+ "lessons/1-Intro/assignment.md": {
+ "original_hash": "a334df77a82aaaf2a29c77065d3e481e",
+ "translation_date": "2025-11-18T21:42:25+00:00",
+ "source_file": "lessons/1-Intro/assignment.md",
+ "language_code": "nl"
+ },
+ "lessons/2-Symbolic/README.md": {
+ "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
+ "translation_date": "2026-01-16T03:06:29+00:00",
+ "source_file": "lessons/2-Symbolic/README.md",
+ "language_code": "nl"
+ },
+ "lessons/2-Symbolic/assignment.md": {
+ "original_hash": "a057a8604f3976c3e309884453f1fad0",
+ "translation_date": "2025-08-28T19:41:16+00:00",
+ "source_file": "lessons/2-Symbolic/assignment.md",
+ "language_code": "nl"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/README.md": {
+ "original_hash": "c34cbba802058b6fa267e1a294d4e510",
+ "translation_date": "2025-09-23T10:12:05+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
+ "language_code": "nl"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
+ "original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
+ "translation_date": "2025-08-29T11:41:19+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
+ "original_hash": "789d6c3fb6fc7948a470b33078a5983a",
+ "translation_date": "2025-09-23T10:11:46+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
+ "language_code": "nl"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
+ "original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
+ "translation_date": "2025-08-28T19:47:42+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/README.md": {
+ "original_hash": "ddd216f558a255260a9374008002c971",
+ "translation_date": "2025-09-23T10:12:23+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
+ "language_code": "nl"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
+ "original_hash": "e452d897efb9a89700f41021834cf6e5",
+ "translation_date": "2025-08-28T19:50:57+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/3-NeuralNetworks/README.md": {
+ "original_hash": "f862a99d88088163df12270e2f2ad6c3",
+ "translation_date": "2025-10-03T12:50:21+00:00",
+ "source_file": "lessons/3-NeuralNetworks/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/README.md": {
+ "original_hash": "feeca98225cb420afc89415f24f63d92",
+ "translation_date": "2025-09-23T10:07:39+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
+ "original_hash": "3d53d6409f80970f7281a45dee35328a",
+ "translation_date": "2025-08-28T19:31:25+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
+ "original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
+ "translation_date": "2025-09-23T10:07:06+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/README.md": {
+ "original_hash": "a560d5b845962cf33dc102266e409568",
+ "translation_date": "2025-09-23T10:06:48+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
+ "original_hash": "b70fcf7fcee862990f848c679090943f",
+ "translation_date": "2025-10-03T14:55:55+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/README.md": {
+ "original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
+ "translation_date": "2025-09-23T10:07:19+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
+ "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
+ "translation_date": "2025-08-28T19:28:18+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
+ "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
+ "translation_date": "2025-08-28T19:29:25+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/09-Autoencoders/README.md": {
+ "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
+ "translation_date": "2025-09-23T10:08:55+00:00",
+ "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/10-GANs/README.md": {
+ "original_hash": "0ff65b4da07b23697235de2beb2a3c25",
+ "translation_date": "2025-09-23T10:09:35+00:00",
+ "source_file": "lessons/4-ComputerVision/10-GANs/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/README.md": {
+ "original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
+ "translation_date": "2025-09-23T10:08:15+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
+ "original_hash": "ad568d55ae65c856fe929fc2b278510a",
+ "translation_date": "2025-08-28T19:33:30+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/README.md": {
+ "original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
+ "translation_date": "2025-09-23T10:09:20+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
+ "original_hash": "365f0decfe0f47b460bbde8227c5009d",
+ "translation_date": "2025-08-28T19:36:35+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/4-ComputerVision/README.md": {
+ "original_hash": "58a52f000089c1d8906a4daa4ab1169b",
+ "translation_date": "2025-08-28T19:23:25+00:00",
+ "source_file": "lessons/4-ComputerVision/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/13-TextRep/README.md": {
+ "original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
+ "translation_date": "2025-09-23T10:14:53+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/13-TextRep/assignment.md": {
+ "original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
+ "translation_date": "2025-08-28T20:09:52+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/assignment.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/14-Embeddings/README.md": {
+ "original_hash": "b708c9b85b833864c73c6281f1e6b96e",
+ "translation_date": "2025-09-23T10:14:33+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/14-Embeddings/assignment.md": {
+ "original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
+ "translation_date": "2025-08-28T20:08:27+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/15-LanguageModeling/README.md": {
+ "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
+ "translation_date": "2025-09-23T10:13:09+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/15-LanguageModeling/lab/README.md": {
+ "original_hash": "5130f01fdc5ebb83032b23d489027aac",
+ "translation_date": "2025-08-28T20:00:42+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/16-RNN/README.md": {
+ "original_hash": "e2273cc150380a5e191903cea858f021",
+ "translation_date": "2025-09-23T10:14:12+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/16-RNN/assignment.md": {
+ "original_hash": "47f7d3c6a5373543e051e4d1140ce898",
+ "translation_date": "2025-08-28T20:07:11+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/assignment.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/README.md": {
+ "original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
+ "translation_date": "2025-09-23T10:12:50+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
+ "original_hash": "439e12796197a90e7623d4c9c057b9c2",
+ "translation_date": "2025-08-28T19:59:44+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/18-Transformers/README.md": {
+ "original_hash": "f335dfcb4a993920504c387973a36957",
+ "translation_date": "2025-09-23T10:13:18+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/18-Transformers/assignment.md": {
+ "original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
+ "translation_date": "2025-08-28T20:02:41+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/assignment.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/19-NER/README.md": {
+ "original_hash": "6522312ff835796ca34136a9462fafb2",
+ "translation_date": "2025-09-23T10:13:54+00:00",
+ "source_file": "lessons/5-NLP/19-NER/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/19-NER/lab/README.md": {
+ "original_hash": "032bda5068f543d6c1fcb30c34231461",
+ "translation_date": "2025-08-28T20:05:10+00:00",
+ "source_file": "lessons/5-NLP/19-NER/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/20-LangModels/README.md": {
+ "original_hash": "97836d30a6bec736f8e3b4411c572bc2",
+ "translation_date": "2025-09-23T10:13:37+00:00",
+ "source_file": "lessons/5-NLP/20-LangModels/README.md",
+ "language_code": "nl"
+ },
+ "lessons/5-NLP/README.md": {
+ "original_hash": "8ef02a9318257ea140ed3ed74442096d",
+ "translation_date": "2025-08-28T19:57:15+00:00",
+ "source_file": "lessons/5-NLP/README.md",
+ "language_code": "nl"
+ },
+ "lessons/6-Other/21-GeneticAlgorithms/README.md": {
+ "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
+ "translation_date": "2025-09-23T10:05:41+00:00",
+ "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
+ "language_code": "nl"
+ },
+ "lessons/6-Other/22-DeepRL/README.md": {
+ "original_hash": "04395657fc01648f8f70484d0e55ab67",
+ "translation_date": "2025-09-23T10:06:24+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/README.md",
+ "language_code": "nl"
+ },
+ "lessons/6-Other/22-DeepRL/lab/README.md": {
+ "original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
+ "translation_date": "2025-08-28T19:18:44+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
+ "language_code": "nl"
+ },
+ "lessons/6-Other/23-MultiagentSystems/README.md": {
+ "original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
+ "translation_date": "2025-09-23T10:05:54+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
+ "language_code": "nl"
+ },
+ "lessons/6-Other/23-MultiagentSystems/assignment.md": {
+ "original_hash": "cf654ca60c7f86c8dad28596fb42994b",
+ "translation_date": "2025-08-28T19:17:02+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
+ "language_code": "nl"
+ },
+ "lessons/7-Ethics/README.md": {
+ "original_hash": "437c988596e751072e41a5aad3fcc5d9",
+ "translation_date": "2025-08-28T19:41:44+00:00",
+ "source_file": "lessons/7-Ethics/README.md",
+ "language_code": "nl"
+ },
+ "lessons/README.md": {
+ "original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
+ "translation_date": "2025-08-28T19:14:01+00:00",
+ "source_file": "lessons/README.md",
+ "language_code": "nl"
+ },
+ "lessons/X-Extras/X1-MultiModal/README.md": {
+ "original_hash": "9c592c26aca16ca085d268c732284187",
+ "translation_date": "2025-08-28T19:22:03+00:00",
+ "source_file": "lessons/X-Extras/X1-MultiModal/README.md",
+ "language_code": "nl"
+ },
+ "lessons/sketchnotes/LICENSE.md": {
+ "original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
+ "translation_date": "2025-08-28T19:54:16+00:00",
+ "source_file": "lessons/sketchnotes/LICENSE.md",
+ "language_code": "nl"
+ },
+ "lessons/sketchnotes/README.md": {
+ "original_hash": "050b8bddebafba55b129414e6ab096ab",
+ "translation_date": "2025-08-28T19:51:18+00:00",
+ "source_file": "lessons/sketchnotes/README.md",
+ "language_code": "nl"
+ },
+ "troubleshoot.md": {
+ "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
+ "translation_date": "2025-10-03T09:46:27+00:00",
+ "source_file": "troubleshoot.md",
+ "language_code": "nl"
+ }
+}
\ No newline at end of file
diff --git a/translations/nl/AGENTS.md b/translations/nl/AGENTS.md
index 2a12848e..049be611 100644
--- a/translations/nl/AGENTS.md
+++ b/translations/nl/AGENTS.md
@@ -1,12 +1,3 @@
-
# AGENTS.md
## Projectoverzicht
diff --git a/translations/nl/README.md b/translations/nl/README.md
index 0c856ba5..f65ad0c1 100644
--- a/translations/nl/README.md
+++ b/translations/nl/README.md
@@ -1,12 +1,3 @@
-
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@@ -23,22 +14,23 @@ CO_OP_TRANSLATOR_METADATA:
# Kunstmatige Intelligentie voor Beginners - Een Curriculum
-||
+||
|:---:|
| AI For Beginners - _Sketchnote door [@girlie_mac](https://twitter.com/girlie_mac)_ |
-Verken de wereld van **Kunstmatige Intelligentie** (AI) met ons 12-weken durende curriculum met 24 lessen! Het bevat praktische lessen, quizzen en labs. Het curriculum is geschikt voor beginners en behandelt tools zoals TensorFlow en PyTorch, evenals ethiek in AI.
+Verken de wereld van **Kunstmatige Intelligentie** (AI) met ons 12-weken durend, 24-lessen curriculum! Het bevat praktische lessen, quizzen en labs. Het curriculum is geschikt voor beginners en behandelt tools zoals TensorFlow en PyTorch, evenals ethiek binnen AI.
+
### 🌐 Meertalige Ondersteuning
-#### Ondersteund via GitHub Action (Geautomatiseerd & Altijd Actueel)
+#### Ondersteund via GitHub Action (Geautomatiseerd & Altijd Up-to-Date)
-[Arabisch](../ar/README.md) | [Bengaals](../bn/README.md) | [Bulgaars](../bg/README.md) | [Birmaans (Myanmar)](../my/README.md) | [Chinees (Vereenvoudigd)](../zh/README.md) | [Chinees (Traditioneel, Hong Kong)](../hk/README.md) | [Chinees (Traditioneel, Macau)](../mo/README.md) | [Chinees (Traditioneel, Taiwan)](../tw/README.md) | [Kroatisch](../hr/README.md) | [Tsjechisch](../cs/README.md) | [Deens](../da/README.md) | [Nederlands](./README.md) | [Ests](../et/README.md) | [Fins](../fi/README.md) | [Frans](../fr/README.md) | [Duits](../de/README.md) | [Grieks](../el/README.md) | [Hebreeuws](../he/README.md) | [Hindi](../hi/README.md) | [Hongaars](../hu/README.md) | [Indonesisch](../id/README.md) | [Italiaans](../it/README.md) | [Japans](../ja/README.md) | [Kannada](../kn/README.md) | [Koreaans](../ko/README.md) | [Litouws](../lt/README.md) | [Maleis](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepalees](../ne/README.md) | [Nigeriaans Pidgin](../pcm/README.md) | [Noors](../no/README.md) | [Perzisch (Farsi)](../fa/README.md) | [Pools](../pl/README.md) | [Portugees (Brazilië)](../br/README.md) | [Portugees (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Roemeens](../ro/README.md) | [Russisch](../ru/README.md) | [Servisch (Cyrillisch)](../sr/README.md) | [Slowaaks](../sk/README.md) | [Sloveens](../sl/README.md) | [Spaans](../es/README.md) | [Swahili](../sw/README.md) | [Zweeds](../sv/README.md) | [Tagalog (Filipijns)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thais](../th/README.md) | [Turks](../tr/README.md) | [Oekraïens](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamees](../vi/README.md)
+[Arabisch](../ar/README.md) | [Bengaals](../bn/README.md) | [Bulgaars](../bg/README.md) | [Birmaans (Myanmar)](../my/README.md) | [Chinees (Vereenvoudigd)](../zh-CN/README.md) | [Chinees (Traditioneel, Hong Kong)](../zh-HK/README.md) | [Chinees (Traditioneel, Macau)](../zh-MO/README.md) | [Chinees (Traditioneel, Taiwan)](../zh-TW/README.md) | [Kroatisch](../hr/README.md) | [Tsjechisch](../cs/README.md) | [Deens](../da/README.md) | [Nederlands](./README.md) | [Ests](../et/README.md) | [Fins](../fi/README.md) | [Frans](../fr/README.md) | [Duits](../de/README.md) | [Grieks](../el/README.md) | [Hebreeuws](../he/README.md) | [Hindi](../hi/README.md) | [Hongaars](../hu/README.md) | [Indonesisch](../id/README.md) | [Italiaans](../it/README.md) | [Japans](../ja/README.md) | [Kannada](../kn/README.md) | [Koreaans](../ko/README.md) | [Litouws](../lt/README.md) | [Maleis](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepalees](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Noors](../no/README.md) | [Perzisch (Farsi)](../fa/README.md) | [Pools](../pl/README.md) | [Portugees (Brazilië)](../pt-BR/README.md) | [Portugees (Portugal)](../pt-PT/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Roemeens](../ro/README.md) | [Russisch](../ru/README.md) | [Servisch (Cyrillisch)](../sr/README.md) | [Slowaaks](../sk/README.md) | [Sloveens](../sl/README.md) | [Spaans](../es/README.md) | [Swahili](../sw/README.md) | [Zweeds](../sv/README.md) | [Tagalog (Filipijns)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thais](../th/README.md) | [Turks](../tr/README.md) | [Oekraïens](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamees](../vi/README.md)
> **Lieber lokaal klonen?**
-> Deze repository bevat 50+ vertalingen, wat de downloadgrootte aanzienlijk vergroot. Gebruik sparse checkout om zonder vertalingen te klonen:
+> Deze repository bevat meer dan 50 taalvertalingen wat de downloadgrootte aanzienlijk vergroot. Om te klonen zonder vertalingen, gebruik sparse checkout:
> ```bash
> git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git
> cd AI-For-Beginners
@@ -47,180 +39,180 @@ Verken de wereld van **Kunstmatige Intelligentie** (AI) met ons 12-weken durende
> Dit geeft je alles wat je nodig hebt om de cursus te voltooien met een veel snellere download.
-**Als je extra vertalingen wilt laten ondersteunen, zijn de ondersteunde talen [hier](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md) vermeld**
+**Indien je extra vertaaltalen wenst te ondersteunen, zijn deze hier genoemd [hier](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
## Word lid van de Community
[](https://discord.gg/nTYy5BXMWG)
-## Wat je zult leren
+## Wat je zal leren
**[Mindmap van de Cursus](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
In dit curriculum leer je:
-* Verschillende benaderingen van Kunstmatige Intelligentie, inclusief de "goede oude" symbolische aanpak met **Kennisrepresentatie** en redeneren ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
-* **Neurale Netwerken** en **Deep Learning**, die de kern vormen van moderne AI. We zullen de concepten achter deze belangrijke onderwerpen illustreren met code in twee van de populairste frameworks - [TensorFlow](http://Tensorflow.org) en [PyTorch](http://pytorch.org).
-* **Neurale Architecturen** voor het werken met afbeeldingen en tekst. We behandelen recente modellen maar misschien niet de allernieuwste.
+* Verschillende benaderingen van Kunstmatige Intelligentie, inclusief de "good old" symbolische benadering met **Kennisrepresentatie** en redeneren ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
+* **Neurale Netwerken** en **Diep Leren**, die de kern vormen van moderne AI. We zullen de concepten achter deze belangrijke onderwerpen illustreren met code in twee van de populairste frameworks - [TensorFlow](http://Tensorflow.org) en [PyTorch](http://pytorch.org).
+* **Neurale Architecturen** voor het werken met afbeeldingen en tekst. We behandelen recente modellen maar het kan iets minder up-to-date zijn met de state-of-the-art.
* Minder populaire AI-benaderingen, zoals **Genetische Algoritmen** en **Multi-Agent Systemen**.
Wat we niet behandelen in dit curriculum:
-> [Vind alle aanvullende bronnen voor deze cursus in onze Microsoft Learn collectie](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
+> [Vind alle aanvullende bronnen voor deze cursus in onze Microsoft Learn-collectie](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
-* Business cases voor het gebruik van **AI in Bedrijven**. Overweeg de leerlijn [Introductie tot AI voor zakelijke gebruikers](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) op Microsoft Learn, of [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), ontwikkeld in samenwerking met [INSEAD](https://www.insead.edu/).
-* **Klassieke Machine Learning**, die goed wordt beschreven in ons [Machine Learning voor Beginners Curriculum](http://github.com/Microsoft/ML-for-Beginners).
-* Praktische AI-toepassingen gebouwd met **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Hiervoor raden we aan te starten met Microsoft Learn modules voor [visie](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [natuurlijke taalverwerking](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generative AI met Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** en andere.
-* Specifieke ML **Cloud Frameworks**, zoals [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), of [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Overweeg gebruik te maken van de leerlijnen [Build and operate machine learning solutions with Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) en [Build and Operate Machine Learning Solutions with Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
-* **Conversational AI** en **Chatbots**. Er is een aparte leerlijn [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), en je kunt ook verwijzen naar [deze blogpost](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) voor meer detail.
-* **Diepe Wiskunde** achter deep learning. Hiervoor raden we [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) aan van Ian Goodfellow, Yoshua Bengio en Aaron Courville, dat ook online beschikbaar is op [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
+* Business cases voor het gebruik van **AI in Business**. Overweeg om de leerroute [Introductie tot AI voor zakelijke gebruikers](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) op Microsoft Learn te volgen, of de [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), ontwikkeld in samenwerking met [INSEAD](https://www.insead.edu/).
+* **Klassiek Machine Learning**, dat goed beschreven wordt in ons [Machine Learning voor Beginners Curriculum](http://github.com/Microsoft/ML-for-Beginners).
+* Praktische AI-toepassingen gebouwd met **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. Hiervoor raden we je aan te starten met modules op Microsoft Learn voor [visie](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [natuurlijke taalverwerking](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generatieve AI met Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** en anderen.
+* Specifieke ML **Cloud Frameworks**, zoals [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), of [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Overweeg het gebruik van de leerpaden [Bouw en beheer machine learning-oplossingen met Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) en [Bouw en beheer machine learning-oplossingen met Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
+* **Conversational AI** en **Chatbots**. Er is een aparte leerroute [Maak conversational AI-oplossingen](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum), en je kunt ook verwijzen naar [deze blogpost](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) voor meer details.
+* **Diepe wiskunde** achter diep leren. Hiervoor raden we [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) aan van Ian Goodfellow, Yoshua Bengio en Aaron Courville, dat ook online beschikbaar is op [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
-Voor een zachte introductie tot _AI in de Cloud_-onderwerpen kun je overwegen de leerlijn [Starten met kunstmatige intelligentie op Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) te volgen.
+Voor een zachte introductie tot _AI in de Cloud_ onderwerpen kun je overwegen om de leerroute [Begin met kunstmatige intelligentie op Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) te volgen.
# Inhoud
-| | Leslink | PyTorch/Keras/TensorFlow | Lab |
+| | Les Link | PyTorch/Keras/TensorFlow | Lab |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
-| 0 | [Cursusconfiguratie](./lessons/0-course-setup/setup.md) | [Stel je ontwikkelomgeving in](./lessons/0-course-setup/how-to-run.md) | |
+| 0 | [Cursus Setup](./lessons/0-course-setup/setup.md) | [Stel je ontwikkelomgeving in](./lessons/0-course-setup/how-to-run.md) | |
| I | [**Introductie tot AI**](./lessons/1-Intro/README.md) | | |
| 01 | [Introductie en Geschiedenis van AI](./lessons/1-Intro/README.md) | - | - |
| II | **Symbolische AI** |
-| 02 | [Kennisrepresentatie en Expert Systemen](./lessons/2-Symbolic/README.md) | [Expert Systemen](./lessons/2-Symbolic/Animals.ipynb) / [Ontologie](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Conceptgrafiek](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
+| 02 | [Kennisrepresentatie en Expertsystemen](./lessons/2-Symbolic/README.md) | [Expertsystemen](./lessons/2-Symbolic/Animals.ipynb) / [Ontologie](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Conceptgrafiek](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Introductie tot Neurale Netwerken**](./lessons/3-NeuralNetworks/README.md) |||
| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Notebook](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Lab](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
-| 04 | [Multi-Layered Perceptron en het maken van ons eigen Framework](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notebook](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
+| 04 | [Multi-Layered Perceptron en het creëren van ons eigen Framework](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notebook](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
| 05 | [Introductie tot Frameworks (PyTorch/TensorFlow) en Overfitting](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
| IV | [**Computer Vision**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Verken Computer Vision op Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
| 06 | [Introductie tot Computer Vision. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notebook](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
-| 07 | [Convolutional Neural Networks](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN Architectures](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Lab](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
-| 08 | [Voorgetrainde Netwerken en Transfer Learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) en [Training Tricks](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
-| 09 | [Auto-encoders en VAE’s](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
-| 10 | [Generatieve Tegenstrijdige Netwerken & Artistieke Stijltransfer](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
+| 07 | [Convolutional Neural Networks](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN Architecturen](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Lab](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
+| 08 | [Voorgetrainde Netwerken en Transfer Learning](./lessons/4-ComputerVision/08-TransferLearning/README.md) en [Training Trucs](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
+| 09 | [Autoencoders en VAEs](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
+| 10 | [Generative Adversarial Networks & Artistieke Stijltransfer](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
| 11 | [Objectdetectie](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Lab](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
-| 12 | [Semantische segmentatie. U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | |
+| 12 | [Semantische Segmentatie. U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | |
| V | [**Natuurlijke Taalverwerking**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Verken Natuurlijke Taalverwerking op Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
-| 13 | [Tekstreprentatie. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | |
-| 14 | [Semantische woordembeddings. Word2Vec en GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
-| 15 | [Taalmodellering. Train je eigen embeddings](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
+| 13 | [Tekstrepresentatie. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | |
+| 14 | [Semantische woord-embeddings. Word2Vec en GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
+| 15 | [Taalkundige Modellering. Train je eigen embeddings](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
| 16 | [Recurrent Neural Networks](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | |
| 17 | [Generatieve Recurrente Netwerken](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [Lab](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
| 18 | [Transformers. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | |
| 19 | [Named Entity Recognition](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Lab](./lessons/5-NLP/19-NER/lab/README.md) |
-| 20 | [Grote Taalmodellen, Prompt Programmeren en Few-Shot Taken](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
-| VI | **Andere AI-technieken** || |
+| 20 | [Grote Taalmodellen, Promptprogrammering en Few-Shot Taken](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
+| VI | **Andere AI-Technieken** || |
| 21 | [Genetische Algoritmen](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
| 22 | [Deep Reinforcement Learning](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) |
| 23 | [Multi-Agent Systemen](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
| VII | **AI-ethiek** | | |
-| 24 | [AI-ethiek en Verantwoordelijke AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Principes voor Verantwoordelijke AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
-| IX | **Extras** | | |
+| 24 | [AI-ethiek en Verantwoordelijke AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Verantwoordelijke AI Principes](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
+| IX | **Extra's** | | |
| 25 | [Multi-Modal Netwerken, CLIP en VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
## Elke les bevat
* Voorleesmateriaal
-* Uitvoerbare Jupyter Notebooks, die vaak specifiek zijn voor het framework (**PyTorch** of **TensorFlow**). Het uitvoerbare notebook bevat ook veel theoretisch materiaal, dus om het onderwerp te begrijpen moet je minstens één versie van het notebook doorlopen (ofwel PyTorch of TensorFlow).
-* **Labs** beschikbaar voor sommige onderwerpen, die je de mogelijkheid geven om het geleerde materiaal toe te passen op een specifiek probleem.
+* Uitvoerbare Jupyter Notebooks, die vaak specifiek zijn voor het framework (**PyTorch** of **TensorFlow**). Het uitvoerbare notebook bevat ook veel theoretisch materiaal, dus om het onderwerp te begrijpen moet je minstens één versie van het notebook doorlopen (PyTorch of TensorFlow).
+* **Labs** beschikbaar voor sommige onderwerpen, die je de kans geven om de geleerde stof toe te passen op een specifiek probleem.
* Sommige secties bevatten links naar [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) modules die gerelateerde onderwerpen behandelen.
## Aan de slag
-### 🎯 Nieuw in AI? Begin hier!
+### 🎯 Nieuw met AI? Begin hier!
-Als je helemaal nieuw bent in AI en snel praktische voorbeelden wilt, bekijk dan onze [**Beginnersvriendelijke Voorbeelden**](./examples/README.md)! Deze omvatten:
+Als je helemaal nieuw bent met AI en snel praktische voorbeelden wilt bekijken, bekijk dan onze [**Beginnervriendelijke Voorbeelden**](./examples/README.md)! Deze bevatten:
- 🌟 **Hallo AI Wereld** - Je eerste AI-programma (patroonherkenning)
- 🧠 **Eenvoudig Neuraal Netwerk** - Bouw een neuraal netwerk vanaf nul
-- 🖼️ **Beeldclassificatie** - Beelden classificeren met gedetailleerde uitleg
-- 💬 **Tekst Sentiment** - Analyseer positieve/negatieve tekst
+- 🖼️ **Beeldclassificatie** - Classificeer afbeeldingen met gedetailleerde opmerkingen
+- 💬 **Tekstsentiment** - Analyseer positieve/negatieve tekst
-Deze voorbeelden zijn ontworpen om je te helpen AI-concepten te begrijpen voordat je aan het volledige curriculum begint.
+Deze voorbeelden zijn ontworpen om je te helpen AI-concepten te begrijpen voordat je aan het volledige curriculum begint.
-### 📚 Volledige Curriculum Setup
+### 📚 Volledige Curriculum Setup
-- We hebben een [opstartles](./lessons/0-course-setup/setup.md) gemaakt om je te helpen met het opzetten van je ontwikkelomgeving. - Voor docenten hebben we ook een [curriculum setup-les](./lessons/0-course-setup/for-teachers.md) gemaakt!
-- Hoe je [de code draait in VSCode of een Codespace](./lessons/0-course-setup/how-to-run.md)
+- We hebben een [setup les](./lessons/0-course-setup/setup.md) gemaakt om je te helpen bij het instellen van je ontwikkelomgeving. - Voor docenten hebben we ook een [curricula setup les](./lessons/0-course-setup/for-teachers.md) gemaakt!
+- Hoe de [code uit te voeren in VSCode of een Codespace](./lessons/0-course-setup/how-to-run.md)
-Volg deze stappen:
+Volg deze stappen:
-Fork de Repository: Klik op de knop "Fork" rechtsboven op deze pagina.
+Fork de Repository: Klik op de knop "Fork" rechtsboven op deze pagina.
-Clone de Repository: `git clone https://github.com/microsoft/AI-For-Beginners.git`
+Clone de Repository: `git clone https://github.com/microsoft/AI-For-Beginners.git`
-Vergeet niet deze repo te voorzien van een ster (🌟) zodat je hem later gemakkelijker terugvindt.
+Vergeet niet deze repo te voorzien van een ster (🌟) zodat je hem later gemakkelijker terugvindt.
-## Ontmoet andere Leerlingen
+## Ontmoet andere Leerlingen
-Word lid van onze [officiële AI Discord server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) om andere leerlingen die deze cursus volgen te ontmoeten en netwerken en ondersteuning te krijgen.
+Doe mee met onze [officiële AI Discord-server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) om andere leerlingen die deze cursus volgen te ontmoeten en netwerk te bouwen en ondersteuning te krijgen.
-Als je productfeedback of vragen hebt tijdens het bouwen, bezoek dan ons [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
+Als je productfeedback of vragen hebt tijdens het bouwen, bezoek dan ons [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
-## Quizzen
+## Quizzen
-> **Een opmerking over quizzen**: Alle quizzen bevinden zich in de Quiz-app map in etc\quiz-app, of [Online Hier](https://ff-quizzes.netlify.app/) Ze zijn gekoppeld vanuit de lessen; de quiz-app kan lokaal worden uitgevoerd of naar Azure worden gedeployed; volg de instructies in de `quiz-app` map. Ze worden geleidelijk gelokaliseerd.
+> **Een opmerking over quizzen**: Alle quizzen zitten in de Quiz-app map in etc\quiz-app, of [Online Hier](https://ff-quizzes.netlify.app/) Ze zijn gelinkt vanuit de lessen, de quiz-app kan lokaal worden uitgevoerd of op Azure worden gedeployed; volg de instructies in de `quiz-app` map. Ze worden geleidelijk gelokaliseerd.
-## Hulp Gevraagd
+## Hulp Gezocht
-Heb je suggesties of spelling- of codefouten gevonden? Maak een issue aan of doe een pull request.
+Heb je suggesties of spelling- of codefouten gevonden? Maak een issue aan of dien een pull request in.
-## Speciale Dank
+## Speciale Dank
-* **✍️ Hoofdauteur:** [Dmitry Soshnikov](http://soshnikov.com), PhD
-* **🔥 Editor:** [Jen Looper](https://twitter.com/jenlooper), PhD
-* **🎨 Sketchnote illustrator:** [Tomomi Imura](https://twitter.com/girlie_mac)
-* **✅ Quiz Maker:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
-* **🙏 Kernbijdragers:** [Evgenii Pishchik](https://github.com/Pe4enIks)
+* **✍️ Hoofdauteur:** [Dmitry Soshnikov](http://soshnikov.com), PhD
+* **🔥 Editor:** [Jen Looper](https://twitter.com/jenlooper), PhD
+* **🎨 Sketchnote illustrator:** [Tomomi Imura](https://twitter.com/girlie_mac)
+* **✅ Quiz Maker:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
+* **🙏 Kernbijdragers:** [Evgenii Pishchik](https://github.com/Pe4enIks)
-## Andere Curricula
+## Andere Curricula
-Ons team produceert andere curricula! Bekijk:
+Ons team maakt nog meer curricula! Bekijk:
-
-### LangChain
-[](https://aka.ms/langchain4j-for-beginners)
-[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
+
+### LangChain
+[](https://aka.ms/langchain4j-for-beginners)
+[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
----
+---
-### Azure / Edge / MCP / Agents
-[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
+### Azure / Edge / MCP / Agents
+[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
----
-
-### Generatieve AI Serie
-[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
-[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
-[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
+---
+
+### Generatieve AI Serie
+[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
+[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
+[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
----
-
-### Kernleren
-[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
-[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
+---
+
+### Kernleren
+[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
+[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
----
-
-### Copilot Serie
-[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
-
+---
+
+### Copilot Serie
+[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
+
-## Hulp Krijgen
+## Hulp Krijgen
-Als je vastloopt of vragen hebt over het bouwen van AI-apps. Doe mee met mede-leerlingen en ervaren ontwikkelaars in discussies over MCP. Het is een ondersteunende gemeenschap waar vragen welkom zijn en kennis vrij wordt gedeeld.
+Als je vastloopt of vragen hebt over het bouwen van AI-apps. Doe mee met mede-leerlingen en ervaren ontwikkelaars in discussies over MCP. Het is een ondersteunende community waar vragen welkom zijn en kennis vrij gedeeld wordt.
-[](https://discord.gg/nTYy5BXMWG)
+[](https://discord.gg/nTYy5BXMWG)
-Als je productfeedback of fouten tegenkomt tijdens het bouwen, bezoek dan:
+Als je productfeedback of fouten hebt tijdens het bouwen, bezoek dan:
[](https://aka.ms/foundry/forum)
@@ -228,5 +220,5 @@ Als je productfeedback of fouten tegenkomt tijdens het bouwen, bezoek dan:
**Disclaimer**:
-Dit document is vertaald met behulp van de AI-vertalingsservice [Co-op Translator](https://github.com/Azure/co-op-translator). Hoewel wij streven naar nauwkeurigheid, dient u er rekening mee te houden dat automatische vertalingen fouten of onnauwkeurigheden kunnen bevatten. Het oorspronkelijke document in de oorspronkelijke taal dient als de gezaghebbende bron te worden beschouwd. Voor cruciale informatie wordt professionele menselijke vertaling aanbevolen. Wij zijn niet aansprakelijk voor enige misverstanden of verkeerde interpretaties die voortvloeien uit het gebruik van deze vertaling.
+Dit document is vertaald met behulp van de AI-vertalingsservice [Co-op Translator](https://github.com/Azure/co-op-translator). Hoewel we streven naar nauwkeurigheid, dient u er rekening mee te houden dat automatische vertalingen fouten of onjuistheden kunnen bevatten. Het oorspronkelijke document in de oorspronkelijke taal moet als de gezaghebbende bron worden beschouwd. Voor kritieke informatie wordt professionele menselijke vertaling aanbevolen. Wij zijn niet aansprakelijk voor enige misverstanden of verkeerde interpretaties die voortvloeien uit het gebruik van deze vertaling.
\ No newline at end of file
diff --git a/translations/nl/SECURITY.md b/translations/nl/SECURITY.md
index bf43059a..b1f046cf 100644
--- a/translations/nl/SECURITY.md
+++ b/translations/nl/SECURITY.md
@@ -1,12 +1,3 @@
-
## Beveiliging
Microsoft neemt de beveiliging van onze softwareproducten en -diensten serieus, waaronder alle broncode-repositories die worden beheerd via onze GitHub-organisaties, zoals [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin) en [onze GitHub-organisaties](https://opensource.microsoft.com/).
diff --git a/translations/nl/etc/CODE_OF_CONDUCT.md b/translations/nl/etc/CODE_OF_CONDUCT.md
index f223219e..eb7030c6 100644
--- a/translations/nl/etc/CODE_OF_CONDUCT.md
+++ b/translations/nl/etc/CODE_OF_CONDUCT.md
@@ -1,12 +1,3 @@
-
# Microsoft Open Source Gedragscode
Dit project heeft de [Microsoft Open Source Gedragscode](https://opensource.microsoft.com/codeofconduct/) aangenomen.
diff --git a/translations/nl/etc/CONTRIBUTING.md b/translations/nl/etc/CONTRIBUTING.md
index 771631c1..f3baf24e 100644
--- a/translations/nl/etc/CONTRIBUTING.md
+++ b/translations/nl/etc/CONTRIBUTING.md
@@ -1,12 +1,3 @@
-
# Bijdragen
Dit project verwelkomt bijdragen en suggesties. Voor de meeste bijdragen moet je akkoord gaan met een Contributor License Agreement (CLA), waarin je verklaart dat je het recht hebt om, en daadwerkelijk doet, ons de rechten te geven om jouw bijdrage te gebruiken. Voor meer informatie, bezoek https://cla.microsoft.com.
diff --git a/translations/nl/etc/Mindmap.md b/translations/nl/etc/Mindmap.md
index 169a2f24..35ac0c26 100644
--- a/translations/nl/etc/Mindmap.md
+++ b/translations/nl/etc/Mindmap.md
@@ -1,12 +1,3 @@
-
# AI
## [Introductie tot AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
diff --git a/translations/nl/etc/SUPPORT.md b/translations/nl/etc/SUPPORT.md
index 9c1aa944..d8c20f37 100644
--- a/translations/nl/etc/SUPPORT.md
+++ b/translations/nl/etc/SUPPORT.md
@@ -1,12 +1,3 @@
-
# Ondersteuning
## Hoe problemen te melden en hulp te krijgen
diff --git a/translations/nl/etc/TRANSLATIONS.md b/translations/nl/etc/TRANSLATIONS.md
index 7131a9e5..5cd3d40c 100644
--- a/translations/nl/etc/TRANSLATIONS.md
+++ b/translations/nl/etc/TRANSLATIONS.md
@@ -1,12 +1,3 @@
-
# Draag bij door lessen te vertalen
We verwelkomen vertalingen van de lessen in dit curriculum!
diff --git a/translations/nl/etc/quiz-app/README.md b/translations/nl/etc/quiz-app/README.md
index d490c972..a2fbee55 100644
--- a/translations/nl/etc/quiz-app/README.md
+++ b/translations/nl/etc/quiz-app/README.md
@@ -1,12 +1,3 @@
-
# Quizzen
Deze quizzen zijn de pre- en post-lezing quizzen voor het AI-curriculum op https://aka.ms/ai-beginners
diff --git a/translations/nl/examples/README.md b/translations/nl/examples/README.md
index 471d7007..414dc34b 100644
--- a/translations/nl/examples/README.md
+++ b/translations/nl/examples/README.md
@@ -1,12 +1,3 @@
-
# Beginner-Vriendelijke AI Voorbeelden
Welkom! Deze map bevat eenvoudige, zelfstandige voorbeelden om je te helpen beginnen met AI en machine learning. Elk voorbeeld is ontworpen om toegankelijk te zijn voor beginners, met gedetailleerde opmerkingen en stapsgewijze uitleg.
diff --git a/translations/nl/lessons/0-course-setup/for-teachers.md b/translations/nl/lessons/0-course-setup/for-teachers.md
index 25b9b2ff..dbdcf1af 100644
--- a/translations/nl/lessons/0-course-setup/for-teachers.md
+++ b/translations/nl/lessons/0-course-setup/for-teachers.md
@@ -1,12 +1,3 @@
-
# Voor Docenten
Wilt u deze lesstof in uw klas gebruiken? Voel u vrij om dat te doen!
diff --git a/translations/nl/lessons/0-course-setup/how-to-run.md b/translations/nl/lessons/0-course-setup/how-to-run.md
index 28492b03..41da398b 100644
--- a/translations/nl/lessons/0-course-setup/how-to-run.md
+++ b/translations/nl/lessons/0-course-setup/how-to-run.md
@@ -1,12 +1,3 @@
-
# Hoe de code uit te voeren
Dit curriculum bevat veel uitvoerbare voorbeelden en labs die je wilt uitvoeren. Om dit te doen, heb je de mogelijkheid nodig om Python-code uit te voeren in Jupyter Notebooks die als onderdeel van dit curriculum worden meegeleverd. Je hebt verschillende opties om de code uit te voeren:
diff --git a/translations/nl/lessons/0-course-setup/setup.md b/translations/nl/lessons/0-course-setup/setup.md
index c14edf81..8873c403 100644
--- a/translations/nl/lessons/0-course-setup/setup.md
+++ b/translations/nl/lessons/0-course-setup/setup.md
@@ -1,12 +1,3 @@
-
# Aan de slag met dit curriculum
## Ben je een student?
diff --git a/translations/nl/lessons/1-Intro/README.md b/translations/nl/lessons/1-Intro/README.md
index 4bd59e32..16536cf8 100644
--- a/translations/nl/lessons/1-Intro/README.md
+++ b/translations/nl/lessons/1-Intro/README.md
@@ -1,12 +1,3 @@
-
# Introductie tot AI
diff --git a/translations/nl/lessons/1-Intro/assignment.md b/translations/nl/lessons/1-Intro/assignment.md
index 16b69115..8b03dbe5 100644
--- a/translations/nl/lessons/1-Intro/assignment.md
+++ b/translations/nl/lessons/1-Intro/assignment.md
@@ -1,12 +1,3 @@
-
# Game Jam
Games zijn een gebied dat sterk is beïnvloed door ontwikkelingen in AI en ML. In deze opdracht schrijf je een kort essay over een spel dat je leuk vindt en dat is beïnvloed door de evolutie van AI. Het moet een spel zijn dat oud genoeg is om beïnvloed te zijn door verschillende soorten computerverwerkende systemen. Een goed voorbeeld is schaken of Go, maar kijk ook eens naar videogames zoals Pong of Pac-Man. Schrijf een essay waarin je het verleden, heden en de AI-toekomst van het spel bespreekt.
diff --git a/translations/nl/lessons/2-Symbolic/README.md b/translations/nl/lessons/2-Symbolic/README.md
index 7aea7022..073cb1d3 100644
--- a/translations/nl/lessons/2-Symbolic/README.md
+++ b/translations/nl/lessons/2-Symbolic/README.md
@@ -1,15 +1,6 @@
-
# Kennisrepresentatie en Expert Systemen
-
+
> Sketchnote door [Tomomi Imura](https://twitter.com/girlie_mac)
@@ -41,7 +32,7 @@ Meestal definiëren we kennis niet strikt, maar stemmen het af met andere gerela
Dus, het probleem van **kennisrepresentatie** is het vinden van een effectieve manier om kennis binnen een computer te representeren in de vorm van data, om het automatisch bruikbaar te maken. Dit kan worden gezien als een spectrum:
-
+
> Afbeelding door [Dmitry Soshnikov](http://soshnikov.com)
@@ -94,7 +85,7 @@ Block Syntax | Indent | | |
Een van de vroege successen van symbolische AI waren zogenaamde **expert systemen** - computersystemen die ontworpen waren om als een expert te functioneren in een beperkt probleemdomein. Ze waren gebaseerd op een **kennisbasis** die werd geëxtraheerd van een of meerdere menselijke experts, en ze bevatten een **inference engine** die er bovenop redeneerde.
- | 
+ | 
---------------------------------------------|------------------------------------------------
Vereenvoudigde structuur van een menselijk neuronensysteem | Architectuur van een kennisgebaseerd systeem
@@ -106,7 +97,7 @@ Expert systemen zijn opgebouwd als het menselijke redeneringssysteem, dat een **
Als voorbeeld nemen we het volgende expertsysteem om een dier te bepalen op basis van zijn fysieke kenmerken:
-
+
> Afbeelding door [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/nl/lessons/2-Symbolic/assignment.md b/translations/nl/lessons/2-Symbolic/assignment.md
index 279c53fc..b9a0cf1c 100644
--- a/translations/nl/lessons/2-Symbolic/assignment.md
+++ b/translations/nl/lessons/2-Symbolic/assignment.md
@@ -1,12 +1,3 @@
-
# Bouw een Ontologie
Het bouwen van een kennisbank draait om het categoriseren van een model dat feiten over een onderwerp vertegenwoordigt. Kies een onderwerp - zoals een persoon, een plaats of een ding - en bouw vervolgens een model van dat onderwerp. Gebruik enkele van de technieken en strategieën voor modelbouw die in deze les worden beschreven. Een voorbeeld zou zijn het creëren van een ontologie van een woonkamer met meubels, verlichting, enzovoort. Hoe verschilt de woonkamer van de keuken? De badkamer? Hoe weet je dat het een woonkamer is en geen eetkamer? Gebruik [Protégé](https://protege.stanford.edu/) om je ontologie te bouwen.
diff --git a/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/README.md
index 782319f8..3620fb36 100644
--- a/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/README.md
+++ b/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/README.md
@@ -1,12 +1,3 @@
-
# Introductie tot Neurale Netwerken: Perceptron
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@@ -15,7 +6,7 @@ Een van de eerste pogingen om iets te implementeren dat lijkt op een modern neur
| | |
|--------------|-----------|
-| | |
+|
| 
|
> Afbeeldingen [van Wikipedia](https://en.wikipedia.org/wiki/Perceptron)
@@ -34,7 +25,7 @@ y(x) = f(wTx)
waarbij f een stap-activatiefunctie is
-
+
## Het trainen van de Perceptron
diff --git a/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
index cf2a0e85..f1582345 100644
--- a/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
+++ b/translations/nl/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
@@ -1,12 +1,3 @@
-
# Multi-Classificatie met Perceptron
Labopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/README.md
index 1e8b7afa..4241b538 100644
--- a/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/README.md
+++ b/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/README.md
@@ -1,12 +1,3 @@
-
# Introductie tot Neurale Netwerken. Multi-Layered Perceptron
In de vorige sectie heb je geleerd over het eenvoudigste model van een neuraal netwerk: de éénlaagse perceptron, een lineair tweeklassen-classificatiemodel.
@@ -65,7 +56,7 @@ Het gradient descent-algoritme blijft hetzelfde, maar het wordt moeilijker om de
Merk op dat het meest linkse deel van al deze uitdrukkingen hetzelfde is, en dat we dus effectief de afgeleiden kunnen berekenen door te beginnen bij de verliesfunctie en "achterwaarts" door de computationele grafiek te gaan. Daarom wordt de methode voor het trainen van een multi-layered perceptron **backpropagation** genoemd, of 'backprop'.
-
+
> TODO: afbeelding bronvermelding
diff --git a/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
index 4c718e33..c69b3c83 100644
--- a/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
+++ b/translations/nl/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
@@ -1,12 +1,3 @@
-
# MNIST-classificatie met ons eigen framework
Labopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/README.md
index daac5b04..0e079389 100644
--- a/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/README.md
+++ b/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/README.md
@@ -1,12 +1,3 @@
-
# Neural Netwerk Frameworks
Zoals we al hebben geleerd, moeten we twee dingen doen om neurale netwerken efficiënt te kunnen trainen:
diff --git a/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
index 19045b90..ea84304d 100644
--- a/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
+++ b/translations/nl/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Classificatie met PyTorch/TensorFlow
Labopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/3-NeuralNetworks/README.md b/translations/nl/lessons/3-NeuralNetworks/README.md
index cb9b9546..34226f56 100644
--- a/translations/nl/lessons/3-NeuralNetworks/README.md
+++ b/translations/nl/lessons/3-NeuralNetworks/README.md
@@ -1,12 +1,3 @@
-
# Introductie tot Neurale Netwerken
diff --git a/translations/nl/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/nl/lessons/4-ComputerVision/06-IntroCV/README.md
index 954065d6..55cf0dd6 100644
--- a/translations/nl/lessons/4-ComputerVision/06-IntroCV/README.md
+++ b/translations/nl/lessons/4-ComputerVision/06-IntroCV/README.md
@@ -1,12 +1,3 @@
-
# Introductie tot Computer Vision
[Computer Vision](https://wikipedia.org/wiki/Computer_vision) is een vakgebied dat erop gericht is computers een hoog niveau van begrip van digitale afbeeldingen te geven. Dit is een vrij brede definitie, omdat *begrip* veel verschillende dingen kan betekenen, zoals het vinden van een object op een afbeelding (**objectdetectie**), begrijpen wat er gebeurt (**eventdetectie**), een afbeelding beschrijven in tekst, of een scène in 3D reconstrueren. Er zijn ook speciale taken die betrekking hebben op menselijke afbeeldingen: leeftijd- en emotie-inschatting, gezichtsdetectie en -identificatie, en 3D-houdingsinschatting, om er een paar te noemen.
@@ -115,7 +106,7 @@ Lees meer over optische stroom [in deze geweldige tutorial](https://learnopencv.
In deze lab ga je een video maken met eenvoudige gebaren, en jouw doel is om op/neer/links/rechts bewegingen te extraheren met behulp van optische stroom.
-
+
---
diff --git a/translations/nl/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/nl/lessons/4-ComputerVision/06-IntroCV/lab/README.md
index 05bd143f..513ad81f 100644
--- a/translations/nl/lessons/4-ComputerVision/06-IntroCV/lab/README.md
+++ b/translations/nl/lessons/4-ComputerVision/06-IntroCV/lab/README.md
@@ -1,12 +1,3 @@
-
# Bewegingen detecteren met behulp van Optical Flow
Labopdracht uit [AI for Beginners Curriculum](https://aka.ms/ai-beginners).
diff --git a/translations/nl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/nl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
index 157540be..c644427e 100644
--- a/translations/nl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
+++ b/translations/nl/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
@@ -1,12 +1,3 @@
-
# Bekende CNN-Architecturen
### VGG-16
@@ -25,7 +16,7 @@ Zoals je kunt zien, volgt VGG een traditionele piramide-architectuur, wat een op
ResNet is een familie van modellen die in 2015 werd voorgesteld door Microsoft Research. Het belangrijkste idee achter ResNet is het gebruik van **residuele blokken**:
-
+
> Afbeelding uit [dit artikel](https://arxiv.org/pdf/1512.03385.pdf)
@@ -37,7 +28,7 @@ Je kunt dit netwerk ook zien als een model dat zijn complexiteit aanpast aan de
De Google Inception-architectuur gaat nog een stap verder en bouwt elke netwerklaag als een combinatie van verschillende paden:
-
+
> Afbeelding van [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454)
diff --git a/translations/nl/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/nl/lessons/4-ComputerVision/07-ConvNets/README.md
index 8bae1f01..152fc0c6 100644
--- a/translations/nl/lessons/4-ComputerVision/07-ConvNets/README.md
+++ b/translations/nl/lessons/4-ComputerVision/07-ConvNets/README.md
@@ -1,12 +1,3 @@
-
# Convolutionele Neurale Netwerken
We hebben eerder gezien dat neurale netwerken behoorlijk goed zijn in het verwerken van afbeeldingen, en zelfs een perceptron met één laag kan handgeschreven cijfers uit de MNIST-dataset met redelijke nauwkeurigheid herkennen. De MNIST-dataset is echter heel bijzonder, omdat alle cijfers gecentreerd zijn in de afbeelding, wat de taak eenvoudiger maakt.
@@ -24,7 +15,7 @@ Om patronen te extraheren, maken we gebruik van het concept van **convolutionele
Als we bijvoorbeeld 3x3 verticale en horizontale randfilters toepassen op de MNIST-cijfers, kunnen we highlights (bijvoorbeeld hoge waarden) krijgen waar verticale en horizontale randen in onze originele afbeelding zijn. Deze twee filters kunnen dus worden gebruikt om "te zoeken naar" randen. Op dezelfde manier kunnen we verschillende filters ontwerpen om andere laag-niveau patronen te zoeken:
-
+
> Afbeelding van [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
diff --git a/translations/nl/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/nl/lessons/4-ComputerVision/07-ConvNets/lab/README.md
index e6b2e99e..08469188 100644
--- a/translations/nl/lessons/4-ComputerVision/07-ConvNets/lab/README.md
+++ b/translations/nl/lessons/4-ComputerVision/07-ConvNets/lab/README.md
@@ -1,12 +1,3 @@
-
# Classificatie van Huisdiergezichten
Labopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/nl/lessons/4-ComputerVision/08-TransferLearning/README.md
index dc8676af..869ae9c6 100644
--- a/translations/nl/lessons/4-ComputerVision/08-TransferLearning/README.md
+++ b/translations/nl/lessons/4-ComputerVision/08-TransferLearning/README.md
@@ -1,12 +1,3 @@
-
# Voorgetrainde Netwerken en Transfer Learning
Het trainen van CNN's kan veel tijd kosten en vereist een grote hoeveelheid data. Veel tijd wordt besteed aan het leren van de beste laag-niveau filters die een netwerk kan gebruiken om patronen uit afbeeldingen te halen. Een logische vraag is: kunnen we een neuraal netwerk dat op één dataset is getraind gebruiken en aanpassen om andere afbeeldingen te classificeren zonder een volledig trainingsproces?
diff --git a/translations/nl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/nl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
index 28fe4bea..83fe4481 100644
--- a/translations/nl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
+++ b/translations/nl/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
@@ -1,12 +1,3 @@
-
# Deep Learning Training Tricks
Naarmate neurale netwerken dieper worden, wordt het proces van hun training steeds uitdagender. Een groot probleem is het zogenaamde [vanishing gradients](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) of [exploding gradients](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Deze post](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) geeft een goede introductie tot deze problemen.
diff --git a/translations/nl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/nl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
index 82ace5a6..13c94be9 100644
--- a/translations/nl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
+++ b/translations/nl/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
@@ -1,12 +1,3 @@
-
# Classificatie van Oxford Huisdieren met Transfer Learning
Labopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/nl/lessons/4-ComputerVision/09-Autoencoders/README.md
index d9d9b039..0ce92915 100644
--- a/translations/nl/lessons/4-ComputerVision/09-Autoencoders/README.md
+++ b/translations/nl/lessons/4-ComputerVision/09-Autoencoders/README.md
@@ -1,12 +1,3 @@
-
# Autoencoders
Bij het trainen van CNNs is een van de problemen dat we veel gelabelde data nodig hebben. In het geval van beeldclassificatie moeten we afbeeldingen in verschillende klassen indelen, wat een handmatig proces is.
@@ -46,7 +37,7 @@ Samenvattend:
* We nemen een steekproefvector `sample` uit de verdeling N(zmean,exp(zlog\_sigma))
* De decoder probeert de originele afbeelding te decoderen met `sample` als invoervector
-
+ 
> Afbeelding van [deze blogpost](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) door Isaak Dykeman
@@ -57,13 +48,13 @@ Variational autoencoders gebruiken een complexe verliesfunctie die uit twee dele
Een belangrijk voordeel van VAEs is dat ze ons in staat stellen relatief eenvoudig nieuwe afbeeldingen te genereren, omdat we weten uit welke verdeling we latente vectoren moeten nemen. Bijvoorbeeld, als we een VAE trainen met een 2D latente vector op MNIST, kunnen we vervolgens de componenten van de latente vector variëren om verschillende cijfers te krijgen:
-
+
> Afbeelding door [Dmitry Soshnikov](http://soshnikov.com)
Let op hoe afbeeldingen in elkaar overlopen, terwijl we latente vectoren uit verschillende delen van de latente parametersruimte halen. We kunnen deze ruimte ook in 2D visualiseren:
-
+
> Afbeelding door [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/nl/lessons/4-ComputerVision/10-GANs/README.md b/translations/nl/lessons/4-ComputerVision/10-GANs/README.md
index be26fd07..6cb4a2e0 100644
--- a/translations/nl/lessons/4-ComputerVision/10-GANs/README.md
+++ b/translations/nl/lessons/4-ComputerVision/10-GANs/README.md
@@ -1,12 +1,3 @@
-
# Generative Adversarial Networks
In de vorige sectie hebben we geleerd over **generatieve modellen**: modellen die nieuwe afbeeldingen kunnen genereren die lijken op de afbeeldingen in de trainingsdataset. VAE was een goed voorbeeld van een generatief model.
@@ -17,7 +8,7 @@ Als we echter iets echt betekenisvols willen genereren, zoals een schilderij met
Het belangrijkste idee van een GAN is om twee neurale netwerken te hebben die tegen elkaar worden getraind:
-
+
> Afbeelding door [Dmitry Soshnikov](http://soshnikov.com)
@@ -41,7 +32,7 @@ Een Generator is iets ingewikkelder. Je kunt het beschouwen als een omgekeerde d
> ✅ Omdat de convolutielaag wordt geïmplementeerd als een lineair filter dat over de afbeelding beweegt, is deconvolutie in wezen vergelijkbaar met convolutie en kan het worden geïmplementeerd met dezelfde laaglogica.
-
+
> Afbeelding door [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/README.md
index fc098284..4299932e 100644
--- a/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/README.md
+++ b/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/README.md
@@ -1,12 +1,3 @@
-
# Objectdetectie
De beeldclassificatiemodellen die we tot nu toe hebben behandeld, namen een afbeelding en produceerden een categorisch resultaat, zoals de klasse 'nummer' in een MNIST-probleem. Echter, in veel gevallen willen we niet alleen weten dat een afbeelding objecten toont - we willen ook hun exacte locatie bepalen. Dit is precies het doel van **objectdetectie**.
diff --git a/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
index de962a17..18a6f361 100644
--- a/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
+++ b/translations/nl/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
@@ -1,12 +1,3 @@
-
# Hoofddetectie met behulp van Hollywood Heads Dataset
Practicumopdracht uit de [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/nl/lessons/4-ComputerVision/12-Segmentation/README.md
index c39fbc68..69158fce 100644
--- a/translations/nl/lessons/4-ComputerVision/12-Segmentation/README.md
+++ b/translations/nl/lessons/4-ComputerVision/12-Segmentation/README.md
@@ -1,12 +1,3 @@
-
# Segmentatie
We hebben eerder geleerd over Objectdetectie, waarmee we objecten in een afbeelding kunnen lokaliseren door hun *omgrenzende kaders* te voorspellen. Voor sommige taken hebben we echter niet alleen omgrenzende kaders nodig, maar ook een nauwkeurigere objectlokalisatie. Deze taak wordt **segmentatie** genoemd.
@@ -20,7 +11,7 @@ Segmentatie kan worden gezien als **pixelclassificatie**, waarbij we voor **elke
Bij instance segmentatie zijn deze schapen verschillende objecten, maar bij semantische segmentatie worden alle schapen weergegeven als één klasse.
-
+
> Afbeelding afkomstig uit [deze blogpost](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)
@@ -29,7 +20,7 @@ Er zijn verschillende neurale architecturen voor segmentatie, maar ze hebben all
* **Encoder** haalt kenmerken uit de invoerafbeelding.
* **Decoder** zet die kenmerken om in de **maskerafbeelding**, met dezelfde grootte en een aantal kanalen dat overeenkomt met het aantal klassen.
-
+
> Afbeelding afkomstig uit [deze publicatie](https://arxiv.org/pdf/2001.05566.pdf)
@@ -43,7 +34,7 @@ In deze les zullen we segmentatie in actie zien door een netwerk te trainen om m
> ✅ Deze techniek is bijzonder geschikt voor dit type medische beeldvorming, maar welke andere toepassingen in de echte wereld kun je je voorstellen?
-
+
> Afbeelding afkomstig uit de PH2 Database
diff --git a/translations/nl/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/nl/lessons/4-ComputerVision/12-Segmentation/lab/README.md
index 3b21ab4c..3a4d1659 100644
--- a/translations/nl/lessons/4-ComputerVision/12-Segmentation/lab/README.md
+++ b/translations/nl/lessons/4-ComputerVision/12-Segmentation/lab/README.md
@@ -1,12 +1,3 @@
-
# Segmentatie van het Menselijk Lichaam
Praktijkopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/4-ComputerVision/README.md b/translations/nl/lessons/4-ComputerVision/README.md
index abb851c1..52ff2688 100644
--- a/translations/nl/lessons/4-ComputerVision/README.md
+++ b/translations/nl/lessons/4-ComputerVision/README.md
@@ -1,12 +1,3 @@
-
# Computer Vision
diff --git a/translations/nl/lessons/5-NLP/13-TextRep/README.md b/translations/nl/lessons/5-NLP/13-TextRep/README.md
index 8c8917c9..e5c1d179 100644
--- a/translations/nl/lessons/5-NLP/13-TextRep/README.md
+++ b/translations/nl/lessons/5-NLP/13-TextRep/README.md
@@ -1,12 +1,3 @@
-
# Tekst Representeren als Tensors
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/25)
@@ -25,7 +16,7 @@ Ons doel is om het nieuwsitem te classificeren in een van de categorieën op bas
Als we Natural Language Processing (NLP)-taken willen oplossen met neurale netwerken, hebben we een manier nodig om tekst als tensors te representeren. Computers representeren tekstuele karakters al als nummers die corresponderen met lettertypen op je scherm, door middel van coderingen zoals ASCII of UTF-8.
-
+
> [Afbeeldingsbron](https://www.seobility.net/en/wiki/ASCII)
@@ -48,7 +39,7 @@ In sommige gevallen kunnen we overwegen om tri-grammen te gebruiken -- combinati
Bij het oplossen van taken zoals tekstclassificatie moeten we tekst kunnen representeren door één vector van vaste grootte, die we gebruiken als invoer voor de uiteindelijke dense classifier. Een van de eenvoudigste manieren om dit te doen is door alle individuele woordrepresentaties te combineren, bijvoorbeeld door ze op te tellen. Als we de one-hot encodings van elk woord optellen, krijgen we een vector van frequenties, die laat zien hoe vaak elk woord voorkomt in de tekst. Zo'n representatie van tekst wordt **bag of words** (BoW) genoemd.
-
+
> Afbeelding door de auteur
diff --git a/translations/nl/lessons/5-NLP/13-TextRep/assignment.md b/translations/nl/lessons/5-NLP/13-TextRep/assignment.md
index 3365e2a4..8e942388 100644
--- a/translations/nl/lessons/5-NLP/13-TextRep/assignment.md
+++ b/translations/nl/lessons/5-NLP/13-TextRep/assignment.md
@@ -1,12 +1,3 @@
-
# Opdracht: Notebooks
Gebruik de notebooks die bij deze les horen (ofwel de PyTorch- of de TensorFlow-versie) en voer ze opnieuw uit met je eigen dataset, bijvoorbeeld een dataset van Kaggle, gebruikt met bronvermelding. Herschrijf de notebook om je eigen bevindingen te benadrukken. Probeer enkele innovatieve datasets die mogelijk verrassend zijn, zoals [deze over UFO-waarnemingen](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) van NUFORC.
diff --git a/translations/nl/lessons/5-NLP/14-Embeddings/README.md b/translations/nl/lessons/5-NLP/14-Embeddings/README.md
index f4861e02..7272c62d 100644
--- a/translations/nl/lessons/5-NLP/14-Embeddings/README.md
+++ b/translations/nl/lessons/5-NLP/14-Embeddings/README.md
@@ -1,12 +1,3 @@
-
# Embeddings
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/27)
diff --git a/translations/nl/lessons/5-NLP/14-Embeddings/assignment.md b/translations/nl/lessons/5-NLP/14-Embeddings/assignment.md
index 9900a403..a6f3e0cb 100644
--- a/translations/nl/lessons/5-NLP/14-Embeddings/assignment.md
+++ b/translations/nl/lessons/5-NLP/14-Embeddings/assignment.md
@@ -1,12 +1,3 @@
-
# Opdracht: Notebooks
Gebruik de notebooks die bij deze les horen (ofwel de PyTorch- of de TensorFlow-versie) en voer ze opnieuw uit met je eigen dataset, bijvoorbeeld een dataset van Kaggle, gebruikt met bronvermelding. Herschrijf de notebook om je eigen bevindingen te benadrukken. Probeer een ander soort dataset en documenteer je bevindingen, met behulp van tekst zoals [deze Beatles-songteksten](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics).
diff --git a/translations/nl/lessons/5-NLP/15-LanguageModeling/README.md b/translations/nl/lessons/5-NLP/15-LanguageModeling/README.md
index 2917f5e7..954f7d45 100644
--- a/translations/nl/lessons/5-NLP/15-LanguageModeling/README.md
+++ b/translations/nl/lessons/5-NLP/15-LanguageModeling/README.md
@@ -1,12 +1,3 @@
-
# Taalmodellering
Semantische embeddings, zoals Word2Vec en GloVe, zijn eigenlijk een eerste stap richting **taalmodellering** - het creëren van modellen die op een bepaalde manier de aard van de taal *begrijpen* (of *representeren*).
diff --git a/translations/nl/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/nl/lessons/5-NLP/15-LanguageModeling/lab/README.md
index ef61f664..1c774a46 100644
--- a/translations/nl/lessons/5-NLP/15-LanguageModeling/lab/README.md
+++ b/translations/nl/lessons/5-NLP/15-LanguageModeling/lab/README.md
@@ -1,12 +1,3 @@
-
# Skip-Gram Model Trainen
Labopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/5-NLP/16-RNN/README.md b/translations/nl/lessons/5-NLP/16-RNN/README.md
index 2ae8b7f2..74962b0f 100644
--- a/translations/nl/lessons/5-NLP/16-RNN/README.md
+++ b/translations/nl/lessons/5-NLP/16-RNN/README.md
@@ -1,12 +1,3 @@
-
# Recurrent Neural Networks
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/31)
@@ -31,7 +22,7 @@ Laten we eens kijken hoe een eenvoudige RNN-cel is georganiseerd. Het accepteert
Een eenvoudige RNN-cel heeft twee gewichts-matrices binnenin: één transformeert een invoersymbool (laten we het W noemen), en een andere transformeert een invoertoestand (H). In dit geval wordt de uitvoer van het netwerk berekend als σ(W×Xi+H×Si-1+b), waarbij σ de activatiefunctie is en b een extra bias is.
-
+
> Afbeelding door de auteur
diff --git a/translations/nl/lessons/5-NLP/16-RNN/assignment.md b/translations/nl/lessons/5-NLP/16-RNN/assignment.md
index 4845056f..fbb38f16 100644
--- a/translations/nl/lessons/5-NLP/16-RNN/assignment.md
+++ b/translations/nl/lessons/5-NLP/16-RNN/assignment.md
@@ -1,12 +1,3 @@
-
# Opdracht: Notebooks
Gebruik de notebooks die bij deze les horen (ofwel de PyTorch- of de TensorFlow-versie) en voer ze opnieuw uit met je eigen dataset, bijvoorbeeld een dataset van Kaggle, gebruikt met bronvermelding. Herschrijf de notebook om je eigen bevindingen te benadrukken. Probeer een ander soort dataset en documenteer je bevindingen, met tekst zoals [deze Kaggle-competitiedataset over weer-tweets](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv).
diff --git a/translations/nl/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/nl/lessons/5-NLP/17-GenerativeNetworks/README.md
index 0612be7c..99d884a6 100644
--- a/translations/nl/lessons/5-NLP/17-GenerativeNetworks/README.md
+++ b/translations/nl/lessons/5-NLP/17-GenerativeNetworks/README.md
@@ -1,12 +1,3 @@
-
# Generatieve netwerken
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/33)
@@ -36,7 +27,7 @@ We trainen deze RNN om tekst stap voor stap te genereren. Bij elke stap nemen we
Bij het genereren van tekst (tijdens inferentie) beginnen we met een **prompt**, die door de RNN-cellen wordt doorgegeven om de tussenliggende toestand te genereren. Vanuit deze toestand begint de generatie. We genereren één karakter tegelijk en geven de toestand en het gegenereerde karakter door aan een andere RNN-cel om het volgende te genereren, totdat we genoeg karakters hebben gegenereerd.
-
+
> Afbeelding door de auteur
diff --git a/translations/nl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/nl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
index bdcf734c..628f1437 100644
--- a/translations/nl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
+++ b/translations/nl/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Woordniveau Tekstgeneratie met RNNs
Praktijkopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/5-NLP/18-Transformers/README.md b/translations/nl/lessons/5-NLP/18-Transformers/README.md
index 1a64f5a6..e86ed16e 100644
--- a/translations/nl/lessons/5-NLP/18-Transformers/README.md
+++ b/translations/nl/lessons/5-NLP/18-Transformers/README.md
@@ -1,12 +1,3 @@
-
# Aandachtsmechanismen en Transformers
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/35)
@@ -56,7 +47,7 @@ Het idee van positionele codering is als volgt:
* Trainbare embedding, vergelijkbaar met tokenembedding. Dit is de aanpak die we hier beschouwen. We passen embeddinglagen toe op zowel tokens als hun posities, wat resulteert in embeddingvectoren van dezelfde dimensies, die we vervolgens bij elkaar optellen.
* Vaste positionele coderingsfunctie, zoals voorgesteld in het oorspronkelijke artikel.
-
+
> Afbeelding door de auteur
diff --git a/translations/nl/lessons/5-NLP/18-Transformers/assignment.md b/translations/nl/lessons/5-NLP/18-Transformers/assignment.md
index 05e45e7f..386babfb 100644
--- a/translations/nl/lessons/5-NLP/18-Transformers/assignment.md
+++ b/translations/nl/lessons/5-NLP/18-Transformers/assignment.md
@@ -1,12 +1,3 @@
-
# Opdracht: Transformers
Experimenteer met Transformers op HuggingFace! Probeer enkele scripts die zij aanbieden om te werken met de verschillende modellen die beschikbaar zijn op hun site: https://huggingface.co/docs/transformers/run_scripts. Probeer een van hun datasets, importeer vervolgens een eigen dataset uit dit curriculum of van Kaggle en kijk of je interessante teksten kunt genereren. Maak een notebook met je bevindingen.
diff --git a/translations/nl/lessons/5-NLP/19-NER/README.md b/translations/nl/lessons/5-NLP/19-NER/README.md
index 57951ea5..b94c453f 100644
--- a/translations/nl/lessons/5-NLP/19-NER/README.md
+++ b/translations/nl/lessons/5-NLP/19-NER/README.md
@@ -1,12 +1,3 @@
-
# Herkenning van Naam Entities
Tot nu toe hebben we ons voornamelijk gericht op één NLP-taak: classificatie. Er zijn echter ook andere NLP-taken die met neurale netwerken kunnen worden uitgevoerd. Een van die taken is **[Herkenning van Naam Entities](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), waarbij specifieke entiteiten in tekst worden herkend, zoals plaatsen, persoonsnamen, datums, chemische formules, enzovoort.
@@ -17,7 +8,7 @@ Tot nu toe hebben we ons voornamelijk gericht op één NLP-taak: classificatie.
Stel dat je een natuurlijke taal-chatbot wilt ontwikkelen, vergelijkbaar met Amazon Alexa of Google Assistant. Intelligente chatbots werken door te *begrijpen* wat de gebruiker wil via tekstclassificatie op de ingevoerde zin. Het resultaat van deze classificatie is de zogenaamde **intent**, die bepaalt wat de chatbot moet doen.
-
+
> Afbeelding door de auteur
diff --git a/translations/nl/lessons/5-NLP/19-NER/lab/README.md b/translations/nl/lessons/5-NLP/19-NER/lab/README.md
index 999c623e..8d066fe0 100644
--- a/translations/nl/lessons/5-NLP/19-NER/lab/README.md
+++ b/translations/nl/lessons/5-NLP/19-NER/lab/README.md
@@ -1,12 +1,3 @@
-
# NER
Labopdracht uit [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/nl/lessons/5-NLP/20-LangModels/README.md b/translations/nl/lessons/5-NLP/20-LangModels/README.md
index daf93f43..242ee7e8 100644
--- a/translations/nl/lessons/5-NLP/20-LangModels/README.md
+++ b/translations/nl/lessons/5-NLP/20-LangModels/README.md
@@ -1,12 +1,3 @@
-
# Vooraf Getrainde Grote Taalmodellen
Bij al onze eerdere taken trainden we een neuraal netwerk om een bepaalde taak uit te voeren met behulp van een gelabelde dataset. Met grote transformator-modellen, zoals BERT, gebruiken we taalmodellering op een zelf-superviserende manier om een taalmodel te bouwen, dat vervolgens wordt gespecialiseerd voor specifieke downstream-taken met verdere domeinspecifieke training. Het is echter aangetoond dat grote taalmodellen ook veel taken kunnen oplossen zonder ENIGE domeinspecifieke training. Een familie van modellen die daartoe in staat is, wordt **GPT** genoemd: Generative Pre-Trained Transformer.
diff --git a/translations/nl/lessons/5-NLP/README.md b/translations/nl/lessons/5-NLP/README.md
index f11335c7..b2e65aa1 100644
--- a/translations/nl/lessons/5-NLP/README.md
+++ b/translations/nl/lessons/5-NLP/README.md
@@ -1,12 +1,3 @@
-
# Natuurlijke Taalverwerking
diff --git a/translations/nl/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/nl/lessons/6-Other/21-GeneticAlgorithms/README.md
index 06207d29..3ea5daf7 100644
--- a/translations/nl/lessons/6-Other/21-GeneticAlgorithms/README.md
+++ b/translations/nl/lessons/6-Other/21-GeneticAlgorithms/README.md
@@ -1,12 +1,3 @@
-
# Genetische Algoritmen
## [Pre-lecture quiz](https://ff-quizzes.netlify.app/en/ai/quiz/41)
diff --git a/translations/nl/lessons/6-Other/22-DeepRL/README.md b/translations/nl/lessons/6-Other/22-DeepRL/README.md
index c10d6205..5f547dc7 100644
--- a/translations/nl/lessons/6-Other/22-DeepRL/README.md
+++ b/translations/nl/lessons/6-Other/22-DeepRL/README.md
@@ -1,12 +1,3 @@
-
# Deep Reinforcement Learning
Reinforcement learning (RL) wordt gezien als een van de fundamentele machine learning paradigma's, naast supervised learning en unsupervised learning. Terwijl we bij supervised learning vertrouwen op een dataset met bekende uitkomsten, is RL gebaseerd op **leren door te doen**. Bijvoorbeeld, wanneer we voor het eerst een computerspel zien, beginnen we te spelen, zelfs zonder de regels te kennen, en al snel verbeteren we onze vaardigheden simpelweg door te spelen en ons gedrag aan te passen.
@@ -34,7 +25,7 @@ We hebben allemaal moderne balancerende apparaten gezien, zoals de *Segway* of *
Een vereenvoudigde versie van balanceren staat bekend als het **CartPole**-probleem. In de CartPole-wereld hebben we een horizontale slider die naar links of rechts kan bewegen, en het doel is om een verticale paal bovenop de slider te balanceren terwijl deze beweegt.
-
+
Om deze omgeving te creëren en te gebruiken, hebben we een paar regels Python-code nodig:
diff --git a/translations/nl/lessons/6-Other/22-DeepRL/lab/README.md b/translations/nl/lessons/6-Other/22-DeepRL/lab/README.md
index 99f1174b..d0fc906f 100644
--- a/translations/nl/lessons/6-Other/22-DeepRL/lab/README.md
+++ b/translations/nl/lessons/6-Other/22-DeepRL/lab/README.md
@@ -1,12 +1,3 @@
-
## De omgeving
De Mountain Car-omgeving bestaat uit een auto die vastzit in een vallei. Je doel is om uit de vallei te springen en de vlag te bereiken. De acties die je kunt uitvoeren zijn versnellen naar links, versnellen naar rechts, of niets doen. Je kunt de positie van de auto langs de x-as en de snelheid waarnemen.
diff --git a/translations/nl/lessons/6-Other/23-MultiagentSystems/README.md b/translations/nl/lessons/6-Other/23-MultiagentSystems/README.md
index fd85a8b3..2689e1ff 100644
--- a/translations/nl/lessons/6-Other/23-MultiagentSystems/README.md
+++ b/translations/nl/lessons/6-Other/23-MultiagentSystems/README.md
@@ -1,12 +1,3 @@
-
# Multi-Agent Systemen
Een van de mogelijke manieren om intelligentie te bereiken is de zogenaamde **emergente** (of **synergetische**) benadering, die gebaseerd is op het feit dat het gecombineerde gedrag van veel relatief eenvoudige agenten kan resulteren in een algeheel complexer (of intelligenter) gedrag van het systeem als geheel. Theoretisch is dit gebaseerd op de principes van [Collectieve Intelligentie](https://en.wikipedia.org/wiki/Collective_intelligence), [Emergentisme](https://en.wikipedia.org/wiki/Global_brain) en [Evolutionaire Cybernetica](https://en.wikipedia.org/wiki/Global_brain), die stellen dat systemen op een hoger niveau een soort toegevoegde waarde verkrijgen wanneer ze op de juiste manier worden gecombineerd vanuit systemen op een lager niveau (het zogenaamde *principe van metasysteemtransitie*).
@@ -60,7 +51,7 @@ Je kunt [NetLogo downloaden](https://ccl.northwestern.edu/netlogo/download.shtml
Een geweldig aspect van NetLogo is dat het een bibliotheek bevat met werkende modellen die je kunt proberen. Ga naar **File → Models Library**, en je hebt veel categorieën modellen om uit te kiezen.
-
+
> Een screenshot van de modellenbibliotheek door Dmitry Soshnikov
diff --git a/translations/nl/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/nl/lessons/6-Other/23-MultiagentSystems/assignment.md
index 9f062789..1c2ab6df 100644
--- a/translations/nl/lessons/6-Other/23-MultiagentSystems/assignment.md
+++ b/translations/nl/lessons/6-Other/23-MultiagentSystems/assignment.md
@@ -1,12 +1,3 @@
-
# NetLogo Opdracht
Neem een van de modellen uit de bibliotheek van NetLogo en gebruik het om een echte situatie zo nauwkeurig mogelijk te simuleren. Een goed voorbeeld zou zijn om het Virus-model in de map Alternative Visualizations aan te passen om te laten zien hoe het kan worden gebruikt om de verspreiding van COVID-19 te modelleren. Kun je een model bouwen dat de verspreiding van een virus in het echte leven nabootst?
diff --git a/translations/nl/lessons/7-Ethics/README.md b/translations/nl/lessons/7-Ethics/README.md
index cc73b89e..6ec7f942 100644
--- a/translations/nl/lessons/7-Ethics/README.md
+++ b/translations/nl/lessons/7-Ethics/README.md
@@ -1,12 +1,3 @@
-
# Ethische en Verantwoorde AI
Je bent bijna klaar met deze cursus, en ik hoop dat je inmiddels duidelijk ziet dat AI gebaseerd is op een aantal formele wiskundige methoden die ons in staat stellen om relaties in data te vinden en modellen te trainen om bepaalde aspecten van menselijk gedrag na te bootsen. Op dit moment in de geschiedenis beschouwen we AI als een zeer krachtig hulpmiddel om patronen uit data te halen en deze patronen toe te passen om nieuwe problemen op te lossen.
diff --git a/translations/nl/lessons/README.md b/translations/nl/lessons/README.md
index fa9a918d..232c4ebe 100644
--- a/translations/nl/lessons/README.md
+++ b/translations/nl/lessons/README.md
@@ -1,12 +1,3 @@
-
# Overzicht
diff --git a/translations/nl/lessons/X-Extras/X1-MultiModal/README.md b/translations/nl/lessons/X-Extras/X1-MultiModal/README.md
index c54872f9..875eb0a1 100644
--- a/translations/nl/lessons/X-Extras/X1-MultiModal/README.md
+++ b/translations/nl/lessons/X-Extras/X1-MultiModal/README.md
@@ -1,12 +1,3 @@
-
# Multi-Modale Netwerken
Na het succes van transformer-modellen voor het oplossen van NLP-taken, zijn dezelfde of vergelijkbare architecturen toegepast op computervisie-taken. Er is een groeiende interesse in het bouwen van modellen die zowel visuele als natuurlijke taalvaardigheden kunnen *combineren*. Een van deze pogingen is gedaan door OpenAI en heet CLIP en DALL.E.
diff --git a/translations/nl/lessons/sketchnotes/LICENSE.md b/translations/nl/lessons/sketchnotes/LICENSE.md
index 5ff1a64e..7c9b2463 100644
--- a/translations/nl/lessons/sketchnotes/LICENSE.md
+++ b/translations/nl/lessons/sketchnotes/LICENSE.md
@@ -1,12 +1,3 @@
-
Attribution-ShareAlike 4.0 Internationaal
=======================================================================
diff --git a/translations/nl/lessons/sketchnotes/README.md b/translations/nl/lessons/sketchnotes/README.md
index fe747712..2648bd8e 100644
--- a/translations/nl/lessons/sketchnotes/README.md
+++ b/translations/nl/lessons/sketchnotes/README.md
@@ -1,12 +1,3 @@
-
Alle sketchnotes van het curriculum kunnen hier worden gedownload.
🎨 Gemaakt door: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))
diff --git a/translations/nl/troubleshoot.md b/translations/nl/troubleshoot.md
index 4f49f18d..ae68ec92 100644
--- a/translations/nl/troubleshoot.md
+++ b/translations/nl/troubleshoot.md
@@ -1,12 +1,3 @@
-
# AI-For-Beginners Probleemoplossingsgids
Deze gids helpt je bij het oplossen van veelvoorkomende problemen die je kunt tegenkomen bij het gebruik of bijdragen aan de [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners) repository. Elk probleem bevat achtergrondinformatie, symptomen, uitleg en stapsgewijze oplossingen.
diff --git a/translations/no/.co-op-translator.json b/translations/no/.co-op-translator.json
new file mode 100644
index 00000000..4378866a
--- /dev/null
+++ b/translations/no/.co-op-translator.json
@@ -0,0 +1,398 @@
+{
+ "AGENTS.md": {
+ "original_hash": "6b11a37115944252ab3ed04e358d830d",
+ "translation_date": "2025-10-03T09:23:30+00:00",
+ "source_file": "AGENTS.md",
+ "language_code": "no"
+ },
+ "README.md": {
+ "original_hash": "1984fc89dd304a8a33ab5584691a99aa",
+ "translation_date": "2026-01-30T02:04:08+00:00",
+ "source_file": "README.md",
+ "language_code": "no"
+ },
+ "SECURITY.md": {
+ "original_hash": "a583f49d359c7ebba61433e4dfcd05a9",
+ "translation_date": "2025-08-28T15:02:01+00:00",
+ "source_file": "SECURITY.md",
+ "language_code": "no"
+ },
+ "etc/CODE_OF_CONDUCT.md": {
+ "original_hash": "c06b12caf3c901eb3156e3dd5b0aea56",
+ "translation_date": "2025-08-28T16:07:01+00:00",
+ "source_file": "etc/CODE_OF_CONDUCT.md",
+ "language_code": "no"
+ },
+ "etc/CONTRIBUTING.md": {
+ "original_hash": "847a587aa1b83f4d00858183ff3ed18a",
+ "translation_date": "2025-08-28T16:06:41+00:00",
+ "source_file": "etc/CONTRIBUTING.md",
+ "language_code": "no"
+ },
+ "etc/Mindmap.md": {
+ "original_hash": "f2f88dbd2debd38e26149b27b1fd272d",
+ "translation_date": "2025-08-28T16:05:24+00:00",
+ "source_file": "etc/Mindmap.md",
+ "language_code": "no"
+ },
+ "etc/SUPPORT.md": {
+ "original_hash": "fdfc08baee91e402938a2b1f94fe0949",
+ "translation_date": "2025-08-28T16:04:07+00:00",
+ "source_file": "etc/SUPPORT.md",
+ "language_code": "no"
+ },
+ "etc/TRANSLATIONS.md": {
+ "original_hash": "62b3e3ad5182edb905eec649a87eeeb4",
+ "translation_date": "2025-08-28T16:06:15+00:00",
+ "source_file": "etc/TRANSLATIONS.md",
+ "language_code": "no"
+ },
+ "etc/quiz-app/README.md": {
+ "original_hash": "d699cf8509f74baa5b0b838de5cf0662",
+ "translation_date": "2025-08-28T16:07:43+00:00",
+ "source_file": "etc/quiz-app/README.md",
+ "language_code": "no"
+ },
+ "examples/README.md": {
+ "original_hash": "0d1babfdcbeb46525f2db3fbaaa54cd7",
+ "translation_date": "2025-10-03T11:31:39+00:00",
+ "source_file": "examples/README.md",
+ "language_code": "no"
+ },
+ "lessons/0-course-setup/for-teachers.md": {
+ "original_hash": "a094ef9927883de1cfcee51dbd143381",
+ "translation_date": "2025-08-28T15:08:16+00:00",
+ "source_file": "lessons/0-course-setup/for-teachers.md",
+ "language_code": "no"
+ },
+ "lessons/0-course-setup/how-to-run.md": {
+ "original_hash": "a4717bd9103b9f6cd84d534b83534689",
+ "translation_date": "2026-01-16T02:55:55+00:00",
+ "source_file": "lessons/0-course-setup/how-to-run.md",
+ "language_code": "no"
+ },
+ "lessons/0-course-setup/setup.md": {
+ "original_hash": "7b4e5b8956915870d0a0ed3cc5890042",
+ "translation_date": "2025-12-12T19:53:32+00:00",
+ "source_file": "lessons/0-course-setup/setup.md",
+ "language_code": "no"
+ },
+ "lessons/1-Intro/README.md": {
+ "original_hash": "f57e8aa46141fd220b16ffed8f11aec7",
+ "translation_date": "2025-11-18T21:36:22+00:00",
+ "source_file": "lessons/1-Intro/README.md",
+ "language_code": "no"
+ },
+ "lessons/1-Intro/assignment.md": {
+ "original_hash": "a334df77a82aaaf2a29c77065d3e481e",
+ "translation_date": "2025-11-18T21:37:24+00:00",
+ "source_file": "lessons/1-Intro/assignment.md",
+ "language_code": "no"
+ },
+ "lessons/2-Symbolic/README.md": {
+ "original_hash": "f9f06b266b8b2bfc6b8792ff2bb1bea4",
+ "translation_date": "2026-01-16T02:56:13+00:00",
+ "source_file": "lessons/2-Symbolic/README.md",
+ "language_code": "no"
+ },
+ "lessons/2-Symbolic/assignment.md": {
+ "original_hash": "a057a8604f3976c3e309884453f1fad0",
+ "translation_date": "2025-08-28T15:31:07+00:00",
+ "source_file": "lessons/2-Symbolic/assignment.md",
+ "language_code": "no"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/README.md": {
+ "original_hash": "c34cbba802058b6fa267e1a294d4e510",
+ "translation_date": "2025-09-23T09:44:51+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/README.md",
+ "language_code": "no"
+ },
+ "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md": {
+ "original_hash": "ba5d1eb353d20d3e7181066b3c424b99",
+ "translation_date": "2025-08-29T08:32:26+00:00",
+ "source_file": "lessons/3-NeuralNetworks/03-Perceptron/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/README.md": {
+ "original_hash": "789d6c3fb6fc7948a470b33078a5983a",
+ "translation_date": "2025-09-23T09:44:29+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/README.md",
+ "language_code": "no"
+ },
+ "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md": {
+ "original_hash": "48fdd704d483e19bc3d7464074c9fcbe",
+ "translation_date": "2025-08-28T15:38:20+00:00",
+ "source_file": "lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/README.md": {
+ "original_hash": "ddd216f558a255260a9374008002c971",
+ "translation_date": "2025-09-23T09:45:08+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/README.md",
+ "language_code": "no"
+ },
+ "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md": {
+ "original_hash": "e452d897efb9a89700f41021834cf6e5",
+ "translation_date": "2025-08-28T15:42:10+00:00",
+ "source_file": "lessons/3-NeuralNetworks/05-Frameworks/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/3-NeuralNetworks/README.md": {
+ "original_hash": "f862a99d88088163df12270e2f2ad6c3",
+ "translation_date": "2025-10-03T12:49:48+00:00",
+ "source_file": "lessons/3-NeuralNetworks/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/README.md": {
+ "original_hash": "feeca98225cb420afc89415f24f63d92",
+ "translation_date": "2025-09-23T09:39:44+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/06-IntroCV/lab/README.md": {
+ "original_hash": "3d53d6409f80970f7281a45dee35328a",
+ "translation_date": "2025-08-28T15:20:21+00:00",
+ "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md": {
+ "original_hash": "53faab85adfcebd8c10bcd71dc2fa557",
+ "translation_date": "2025-09-23T09:39:01+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/README.md": {
+ "original_hash": "a560d5b845962cf33dc102266e409568",
+ "translation_date": "2025-09-23T09:38:44+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/07-ConvNets/lab/README.md": {
+ "original_hash": "b70fcf7fcee862990f848c679090943f",
+ "translation_date": "2025-10-03T14:55:38+00:00",
+ "source_file": "lessons/4-ComputerVision/07-ConvNets/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/README.md": {
+ "original_hash": "178c0b5ee5395733eb18aec51e71a0a9",
+ "translation_date": "2025-09-23T09:39:16+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md": {
+ "original_hash": "ae074cd940fc2f4dc24fc07b66ccbd99",
+ "translation_date": "2025-08-28T15:17:10+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/08-TransferLearning/lab/README.md": {
+ "original_hash": "7765935c35fcee69b9fe2d0cfd6963e2",
+ "translation_date": "2025-08-28T15:18:01+00:00",
+ "source_file": "lessons/4-ComputerVision/08-TransferLearning/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/09-Autoencoders/README.md": {
+ "original_hash": "1b8d9e1b3a6f1daa864b1ff3dfc3076d",
+ "translation_date": "2025-09-23T09:40:43+00:00",
+ "source_file": "lessons/4-ComputerVision/09-Autoencoders/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/10-GANs/README.md": {
+ "original_hash": "0ff65b4da07b23697235de2beb2a3c25",
+ "translation_date": "2025-09-23T09:41:22+00:00",
+ "source_file": "lessons/4-ComputerVision/10-GANs/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/README.md": {
+ "original_hash": "d76a7eda28de5210c8b1ba50a6216c69",
+ "translation_date": "2025-09-23T09:40:07+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md": {
+ "original_hash": "ad568d55ae65c856fe929fc2b278510a",
+ "translation_date": "2025-08-28T15:23:26+00:00",
+ "source_file": "lessons/4-ComputerVision/11-ObjectDetection/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/README.md": {
+ "original_hash": "6568aaae7e0e4afed4b5d74b5b223700",
+ "translation_date": "2025-09-23T09:41:06+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/12-Segmentation/lab/README.md": {
+ "original_hash": "365f0decfe0f47b460bbde8227c5009d",
+ "translation_date": "2025-08-28T15:26:10+00:00",
+ "source_file": "lessons/4-ComputerVision/12-Segmentation/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/4-ComputerVision/README.md": {
+ "original_hash": "58a52f000089c1d8906a4daa4ab1169b",
+ "translation_date": "2025-08-28T15:11:53+00:00",
+ "source_file": "lessons/4-ComputerVision/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/13-TextRep/README.md": {
+ "original_hash": "dbd3f73e4139f030ecb2e20387d70fee",
+ "translation_date": "2025-09-23T09:47:54+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/13-TextRep/assignment.md": {
+ "original_hash": "cdc1f2e631f055f3473b36d18e4760b3",
+ "translation_date": "2025-08-28T16:03:47+00:00",
+ "source_file": "lessons/5-NLP/13-TextRep/assignment.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/14-Embeddings/README.md": {
+ "original_hash": "b708c9b85b833864c73c6281f1e6b96e",
+ "translation_date": "2025-09-23T09:47:33+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/14-Embeddings/assignment.md": {
+ "original_hash": "bc690ecf68b38d311cc9e12f3144a28c",
+ "translation_date": "2025-08-28T16:02:07+00:00",
+ "source_file": "lessons/5-NLP/14-Embeddings/assignment.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/15-LanguageModeling/README.md": {
+ "original_hash": "7ba20f54a5bfcd6521018cdfb17c7c57",
+ "translation_date": "2025-09-23T09:45:54+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/15-LanguageModeling/lab/README.md": {
+ "original_hash": "5130f01fdc5ebb83032b23d489027aac",
+ "translation_date": "2025-08-28T15:54:13+00:00",
+ "source_file": "lessons/5-NLP/15-LanguageModeling/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/16-RNN/README.md": {
+ "original_hash": "e2273cc150380a5e191903cea858f021",
+ "translation_date": "2025-09-23T09:47:08+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/16-RNN/assignment.md": {
+ "original_hash": "47f7d3c6a5373543e051e4d1140ce898",
+ "translation_date": "2025-08-28T16:00:39+00:00",
+ "source_file": "lessons/5-NLP/16-RNN/assignment.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/README.md": {
+ "original_hash": "51be6057374d01d70e07dd5ec88ebc0d",
+ "translation_date": "2025-09-23T09:45:38+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/17-GenerativeNetworks/lab/README.md": {
+ "original_hash": "439e12796197a90e7623d4c9c057b9c2",
+ "translation_date": "2025-08-28T15:53:10+00:00",
+ "source_file": "lessons/5-NLP/17-GenerativeNetworks/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/18-Transformers/README.md": {
+ "original_hash": "f335dfcb4a993920504c387973a36957",
+ "translation_date": "2025-09-23T09:46:06+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/18-Transformers/assignment.md": {
+ "original_hash": "177f3ea3995d725e6f9f5c66af16edcd",
+ "translation_date": "2025-08-28T15:55:59+00:00",
+ "source_file": "lessons/5-NLP/18-Transformers/assignment.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/19-NER/README.md": {
+ "original_hash": "6522312ff835796ca34136a9462fafb2",
+ "translation_date": "2025-09-23T09:46:53+00:00",
+ "source_file": "lessons/5-NLP/19-NER/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/19-NER/lab/README.md": {
+ "original_hash": "032bda5068f543d6c1fcb30c34231461",
+ "translation_date": "2025-08-28T15:58:28+00:00",
+ "source_file": "lessons/5-NLP/19-NER/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/20-LangModels/README.md": {
+ "original_hash": "97836d30a6bec736f8e3b4411c572bc2",
+ "translation_date": "2025-09-23T09:46:37+00:00",
+ "source_file": "lessons/5-NLP/20-LangModels/README.md",
+ "language_code": "no"
+ },
+ "lessons/5-NLP/README.md": {
+ "original_hash": "8ef02a9318257ea140ed3ed74442096d",
+ "translation_date": "2025-08-28T15:51:26+00:00",
+ "source_file": "lessons/5-NLP/README.md",
+ "language_code": "no"
+ },
+ "lessons/6-Other/21-GeneticAlgorithms/README.md": {
+ "original_hash": "6bbd632dfe6c62e5f66bb51fd78c174a",
+ "translation_date": "2025-09-23T09:37:31+00:00",
+ "source_file": "lessons/6-Other/21-GeneticAlgorithms/README.md",
+ "language_code": "no"
+ },
+ "lessons/6-Other/22-DeepRL/README.md": {
+ "original_hash": "04395657fc01648f8f70484d0e55ab67",
+ "translation_date": "2025-09-23T09:38:25+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/README.md",
+ "language_code": "no"
+ },
+ "lessons/6-Other/22-DeepRL/lab/README.md": {
+ "original_hash": "7bd8dc72040e98e35e7225e34058cd4e",
+ "translation_date": "2025-08-28T15:07:47+00:00",
+ "source_file": "lessons/6-Other/22-DeepRL/lab/README.md",
+ "language_code": "no"
+ },
+ "lessons/6-Other/23-MultiagentSystems/README.md": {
+ "original_hash": "38a1185ae3d54b180378bbd71ae3ef16",
+ "translation_date": "2025-09-23T09:37:47+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/README.md",
+ "language_code": "no"
+ },
+ "lessons/6-Other/23-MultiagentSystems/assignment.md": {
+ "original_hash": "cf654ca60c7f86c8dad28596fb42994b",
+ "translation_date": "2025-08-28T15:06:00+00:00",
+ "source_file": "lessons/6-Other/23-MultiagentSystems/assignment.md",
+ "language_code": "no"
+ },
+ "lessons/7-Ethics/README.md": {
+ "original_hash": "437c988596e751072e41a5aad3fcc5d9",
+ "translation_date": "2025-08-28T15:31:45+00:00",
+ "source_file": "lessons/7-Ethics/README.md",
+ "language_code": "no"
+ },
+ "lessons/README.md": {
+ "original_hash": "5fef1a0b22498d7188959e2a2cb08af7",
+ "translation_date": "2025-08-28T15:02:23+00:00",
+ "source_file": "lessons/README.md",
+ "language_code": "no"
+ },
+ "lessons/X-Extras/X1-MultiModal/README.md": {
+ "original_hash": "9c592c26aca16ca085d268c732284187",
+ "translation_date": "2025-08-28T15:11:13+00:00",
+ "source_file": "lessons/X-Extras/X1-MultiModal/README.md",
+ "language_code": "no"
+ },
+ "lessons/sketchnotes/LICENSE.md": {
+ "original_hash": "45ab63a2cd8f5faef6c9b150618837a4",
+ "translation_date": "2025-08-28T15:48:43+00:00",
+ "source_file": "lessons/sketchnotes/LICENSE.md",
+ "language_code": "no"
+ },
+ "lessons/sketchnotes/README.md": {
+ "original_hash": "050b8bddebafba55b129414e6ab096ab",
+ "translation_date": "2025-08-28T15:42:28+00:00",
+ "source_file": "lessons/sketchnotes/README.md",
+ "language_code": "no"
+ },
+ "troubleshoot.md": {
+ "original_hash": "8d9c5a4a7c7798d699672a22cb7fea86",
+ "translation_date": "2025-10-03T09:45:41+00:00",
+ "source_file": "troubleshoot.md",
+ "language_code": "no"
+ }
+}
\ No newline at end of file
diff --git a/translations/no/AGENTS.md b/translations/no/AGENTS.md
index ee317b3c..f258d881 100644
--- a/translations/no/AGENTS.md
+++ b/translations/no/AGENTS.md
@@ -1,12 +1,3 @@
-
# AGENTS.md
## Prosjektoversikt
diff --git a/translations/no/README.md b/translations/no/README.md
index 16a12cdd..257c1d45 100644
--- a/translations/no/README.md
+++ b/translations/no/README.md
@@ -1,12 +1,3 @@
-
[](https://github.com/microsoft/AI-For-Beginners/blob/main/LICENSE)
[](https://GitHub.com/microsoft/AI-For-Beginners/graphs/contributors/)
[](https://GitHub.com/microsoft/AI-For-Beginners/issues/)
@@ -21,33 +12,34 @@ CO_OP_TRANSLATOR_METADATA:
[](https://discord.gg/nTYy5BXMWG)
-# Kunstig intelligens for nybegynnere – Et pensum
+# Kunstig intelligens for nybegynnere - En læreplan
-||
+||
|:---:|
-| AI for nybegynnere – _Sketchnote av [@girlie_mac](https://twitter.com/girlie_mac)_ |
+| AI For Beginners - _Sketchnote by [@girlie_mac](https://twitter.com/girlie_mac)_ |
+
+Utforsk verden av **kunstig intelligens** (AI) med vår 12-ukers, 24-leksjoners læreplan! Den inkluderer praktiske leksjoner, quizzer og laboratorier. Læreplanen er nybegynnervennlig og dekker verktøy som TensorFlow og PyTorch, samt etikk innen AI.
-Utforsk verdenen av **kunstig intelligens** (KI) med vårt 12-ukers, 24-leksjoners pensum! Det inkluderer praktiske leksjoner, quizzer og laboratorier. Pensumet er nybegynnervennlig og dekker verktøy som TensorFlow og PyTorch, samt etikk i KI.
### 🌐 Flerspråklig støtte
-#### Støttes via GitHub Action (Automatisert & Alltid Oppdatert)
+#### Støttet via GitHub Action (Automatisk og alltid oppdatert)
-[Arabisk](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarsk](../bg/README.md) | [Burmesisk (Myanmar)](../my/README.md) | [Kinesisk (Forenklet)](../zh/README.md) | [Kinesisk (Tradisjonell, Hong Kong)](../hk/README.md) | [Kinesisk (Tradisjonell, Macao)](../mo/README.md) | [Kinesisk (Tradisjonell, Taiwan)](../tw/README.md) | [Kroatisk](../hr/README.md) | [Tsjekkisk](../cs/README.md) | [Dansk](../da/README.md) | [Nederlandsk](../nl/README.md) | [Estisk](../et/README.md) | [Finsk](../fi/README.md) | [Fransk](../fr/README.md) | [Tysk](../de/README.md) | [Gresk](../el/README.md) | [Hebraisk](../he/README.md) | [Hindi](../hi/README.md) | [Ungarsk](../hu/README.md) | [Indonesisk](../id/README.md) | [Italiensk](../it/README.md) | [Japansk](../ja/README.md) | [Kannada](../kn/README.md) | [Koreansk](../ko/README.md) | [Litauisk](../lt/README.md) | [Malaysisk](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepalesisk](../ne/README.md) | [Nigeriansk Pidgin](../pcm/README.md) | [Norsk](./README.md) | [Persisk (Farsi)](../fa/README.md) | [Polsk](../pl/README.md) | [Portugisisk (Brasil)](../br/README.md) | [Portugisisk (Portugal)](../pt/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Rumensk](../ro/README.md) | [Russisk](../ru/README.md) | [Serbisk (Kyrillisk)](../sr/README.md) | [Slovakisk](../sk/README.md) | [Slovensk](../sl/README.md) | [Spansk](../es/README.md) | [Swahili](../sw/README.md) | [Svensk](../sv/README.md) | [Tagalog (Filippinsk)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Tyrkisk](../tr/README.md) | [Ukrainsk](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamesisk](../vi/README.md)
+[Arabic](../ar/README.md) | [Bengali](../bn/README.md) | [Bulgarian](../bg/README.md) | [Burmese (Myanmar)](../my/README.md) | [Chinese (Simplified)](../zh-CN/README.md) | [Chinese (Traditional, Hong Kong)](../zh-HK/README.md) | [Chinese (Traditional, Macau)](../zh-MO/README.md) | [Chinese (Traditional, Taiwan)](../zh-TW/README.md) | [Croatian](../hr/README.md) | [Czech](../cs/README.md) | [Danish](../da/README.md) | [Dutch](../nl/README.md) | [Estonian](../et/README.md) | [Finnish](../fi/README.md) | [French](../fr/README.md) | [German](../de/README.md) | [Greek](../el/README.md) | [Hebrew](../he/README.md) | [Hindi](../hi/README.md) | [Hungarian](../hu/README.md) | [Indonesian](../id/README.md) | [Italian](../it/README.md) | [Japanese](../ja/README.md) | [Kannada](../kn/README.md) | [Korean](../ko/README.md) | [Lithuanian](../lt/README.md) | [Malay](../ms/README.md) | [Malayalam](../ml/README.md) | [Marathi](../mr/README.md) | [Nepali](../ne/README.md) | [Nigerian Pidgin](../pcm/README.md) | [Norwegian](./README.md) | [Persian (Farsi)](../fa/README.md) | [Polish](../pl/README.md) | [Portuguese (Brazil)](../pt-BR/README.md) | [Portuguese (Portugal)](../pt-PT/README.md) | [Punjabi (Gurmukhi)](../pa/README.md) | [Romanian](../ro/README.md) | [Russian](../ru/README.md) | [Serbian (Cyrillic)](../sr/README.md) | [Slovak](../sk/README.md) | [Slovenian](../sl/README.md) | [Spanish](../es/README.md) | [Swahili](../sw/README.md) | [Swedish](../sv/README.md) | [Tagalog (Filipino)](../tl/README.md) | [Tamil](../ta/README.md) | [Telugu](../te/README.md) | [Thai](../th/README.md) | [Turkish](../tr/README.md) | [Ukrainian](../uk/README.md) | [Urdu](../ur/README.md) | [Vietnamese](../vi/README.md)
> **Foretrekker du å klone lokalt?**
-> Dette depotet inkluderer 50+ språkoversettelser som betydelig øker nedlastingsstørrelsen. For å klone uten oversettelser, bruk sparsommelig utvalg:
+> Dette depotet inkluderer 50+ språkoversettelser som øker nedlastingsstørrelsen betydelig. For å klone uten oversettelser, bruk sparse checkout:
> ```bash
> git clone --filter=blob:none --sparse https://github.com/microsoft/AI-For-Beginners.git
> cd AI-For-Beginners
> git sparse-checkout set --no-cone '/*' '!translations' '!translated_images'
> ```
-> Dette gir deg alt du trenger for å fullføre kurset med en mye raskere nedlasting.
+> Dette gir deg alt du trenger for å fullføre kurset med mye raskere nedlasting.
-**Dersom du ønsker ytterligere støttede oversettelsesspråk, er disse listet [her](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
+**Hvis du ønsker at flere oversettelsesspråk skal støttes, finnes de oppført [her](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)**
## Bli med i fellesskapet
[](https://discord.gg/nTYy5BXMWG)
@@ -56,177 +48,178 @@ Utforsk verdenen av **kunstig intelligens** (KI) med vårt 12-ukers, 24-leksjone
**[Tankekart over kurset](http://soshnikov.com/courses/ai-for-beginners/mindmap.html)**
-I dette pensumet vil du lære:
+I denne læreplanen vil du lære:
-* Ulike tilnærminger til kunstig intelligens, inkludert den "gode gamle" symbolske tilnærmingen med **kunnskapsrepresentasjon** og resonnement ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
-* **Neurale nettverk** og **dyp læring**, som er kjernen i moderne KI. Vi vil illustrere konseptene bak disse viktige temaene ved bruk av kode i to av de mest populære rammeverkene - [TensorFlow](http://Tensorflow.org) og [PyTorch](http://pytorch.org).
-* **Neurale arkitekturer** for arbeid med bilder og tekst. Vi vil dekke nyere modeller, men kan mangle noe av det siste innen forskning.
-* Mindre populære KI-tilnærminger, slik som **genetiske algoritmer** og **multi-agent systemer**.
+* Ulike tilnærminger til kunstig intelligens, inkludert den "gode gamle" symbolske tilnærmingen med **Kunnskapsrepresentasjon** og resonnement ([GOFAI](https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence)).
+* **Neurale nettverk** og **dyp læring**, som er kjernen i moderne AI. Vi illustrerer konseptene bak disse viktige temaene med kode i to av de mest populære rammeverkene - [TensorFlow](http://Tensorflow.org) og [PyTorch](http://pytorch.org).
+* **Neurale arkitekturer** for arbeid med bilder og tekst. Vi dekker nylige modeller, men kan være litt mangelfulle i det siste innen teknologien.
+* Mindre populære AI-tilnærminger, som **genetiske algoritmer** og **multi-agent-systemer**.
-Hva vi ikke vil dekke i dette pensumet:
+Hva vi ikke dekker i denne læreplanen:
-> [Finn alle tilleggsmaterialer for dette kurset i vår Microsoft Learn-samling](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
+> [Finn alle tilleggressurser for dette kurset i vår Microsoft Learn-samling](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)
-* Forretningsscenarier for bruk av **KI i næringslivet**. Vurder å ta [Introduction to AI for business users](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum)-læringssti på Microsoft Learn, eller [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), utviklet i samarbeid med [INSEAD](https://www.insead.edu/).
-* **Klassisk maskinlæring**, som er godt beskrevet i vårt [Machine Learning for Beginners Curriculum](http://github.com/Microsoft/ML-for-Beginners).
-* Praktiske KI-applikasjoner bygget med **[Kognitive tjenester](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. For dette anbefaler vi at du starter med Microsoft Learn-moduler for [syn](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [naturlig språkbehandling](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[generativ KI med Azure OpenAI-tjeneste](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** og andre.
-* Spesifikke ML **Cloud-rammeverk**, som [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), eller [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Vurder å bruke læringsstiene [Build and operate machine learning solutions with Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) og [Build and Operate Machine Learning Solutions with Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
-* **Samtale-KI** og **Chat-boter**. Det finnes en egen [Create conversational AI solutions](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) læringssti, og du kan også se [denne bloggposten](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for mer detaljert informasjon.
+* Forretningscase for bruk av **AI i business**. Vurder å ta [Introduksjon til AI for forretningsbrukere](https://docs.microsoft.com/learn/paths/introduction-ai-for-business-users/?WT.mc_id=academic-77998-bethanycheum) læringssti på Microsoft Learn, eller [AI Business School](https://www.microsoft.com/ai/ai-business-school/?WT.mc_id=academic-77998-bethanycheum), utviklet i samarbeid med [INSEAD](https://www.insead.edu/).
+* **Klassisk maskinlæring**, som er godt beskrevet i vår [Maskinlæring for nybegynnere læreplan](http://github.com/Microsoft/ML-for-Beginners).
+* Praktiske AI-applikasjoner bygget med **[Cognitive Services](https://azure.microsoft.com/services/cognitive-services/?WT.mc_id=academic-77998-bethanycheum)**. For dette anbefaler vi at du starter med Microsoft Learn-moduler for [syn](https://docs.microsoft.com/learn/paths/create-computer-vision-solutions-azure-cognitive-services/?WT.mc_id=academic-77998-bethanycheum), [naturlig språkbehandling](https://docs.microsoft.com/learn/paths/explore-natural-language-processing/?WT.mc_id=academic-77998-bethanycheum), **[Generativ AI med Azure OpenAI Service](https://learn.microsoft.com/en-us/training/paths/develop-ai-solutions-azure-openai/?WT.mc_id=academic-77998-bethanycheum)** og andre.
+* Spesifikke ML **sky-rammeverk**, som [Azure Machine Learning](https://azure.microsoft.com/services/machine-learning/?WT.mc_id=academic-77998-bethanycheum), [Microsoft Fabric](https://learn.microsoft.com/en-us/training/paths/get-started-fabric/?WT.mc_id=academic-77998-bethanycheum), eller [Azure Databricks](https://docs.microsoft.com/learn/paths/data-engineer-azure-databricks?WT.mc_id=academic-77998-bethanycheum). Vurder å bruke læringsstiene [Bygg og drift maskinlæringsløsninger med Azure Machine Learning](https://docs.microsoft.com/learn/paths/build-ai-solutions-with-azure-ml-service/?WT.mc_id=academic-77998-bethanycheum) og [Bygg og drift maskinlæringsløsninger med Azure Databricks](https://docs.microsoft.com/learn/paths/build-operate-machine-learning-solutions-azure-databricks/?WT.mc_id=academic-77998-bethanycheum).
+* **Samtale-AI** og **chatbotter**. Det finnes en egen [Lag samtale-AI løsninger](https://docs.microsoft.com/learn/paths/create-conversational-ai-solutions/?WT.mc_id=academic-77998-bethanycheum) læringssti, og du kan også referere til [dette blogginnlegget](https://soshnikov.com/azure/hello-bot-conversational-ai-on-microsoft-platform/) for mer informasjon.
* **Dyp matematikk** bak dyp læring. For dette anbefaler vi [Deep Learning](https://www.amazon.com/Deep-Learning-Adaptive-Computation-Machine/dp/0262035618) av Ian Goodfellow, Yoshua Bengio og Aaron Courville, som også er tilgjengelig online på [https://www.deeplearningbook.org/](https://www.deeplearningbook.org/).
-For en enkel introduksjon til _KI i skyen_-temaer kan du vurdere å ta [Get started with artificial intelligence on Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum) Learning Path.
+For en mild introduksjon til _AI i skyen_ kan du vurdere å ta læringsstien [Kom i gang med kunstig intelligens på Azure](https://docs.microsoft.com/learn/paths/get-started-with-artificial-intelligence-on-azure/?WT.mc_id=academic-77998-bethanycheum).
# Innhold
-| | Leksjonslenke | PyTorch/Keras/TensorFlow | Laboratorium |
+| | Lesson Link | PyTorch/Keras/TensorFlow | Lab |
| :-: | :------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------ |
-| 0 | [Kursoppsett](./lessons/0-course-setup/setup.md) | [Sett opp ditt utviklingsmiljø](./lessons/0-course-setup/how-to-run.md) | |
-| I | [**Introduksjon til KI**](./lessons/1-Intro/README.md) | | |
-| 01 | [Introduksjon og historie om KI](./lessons/1-Intro/README.md) | - | - |
-| II | **Symbolsk KI** |
+| 0 | [Course Setup](./lessons/0-course-setup/setup.md) | [Setup Your Development Environment](./lessons/0-course-setup/how-to-run.md) | |
+| I | [**Introduksjon til AI**](./lessons/1-Intro/README.md) | | |
+| 01 | [Introduksjon og historien til AI](./lessons/1-Intro/README.md) | - | - |
+| II | **Symbolsk AI** |
| 02 | [Kunnskapsrepresentasjon og ekspertsystemer](./lessons/2-Symbolic/README.md) | [Ekspertsystemer](./lessons/2-Symbolic/Animals.ipynb) / [Ontologi](./lessons/2-Symbolic/FamilyOntology.ipynb) /[Konseptgraf](./lessons/2-Symbolic/MSConceptGraph.ipynb) | |
| III | [**Introduksjon til nevrale nettverk**](./lessons/3-NeuralNetworks/README.md) |||
-| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Notebook](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Lab](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
-| 04 | [Multi-Layered Perceptron og Lage vårt eget rammeverk](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notebook](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
+| 03 | [Perceptron](./lessons/3-NeuralNetworks/03-Perceptron/README.md) | [Notatbok](./lessons/3-NeuralNetworks/03-Perceptron/Perceptron.ipynb) | [Lab](./lessons/3-NeuralNetworks/03-Perceptron/lab/README.md) |
+| 04 | [Flerlaget Perceptron og lage vårt eget rammeverk](./lessons/3-NeuralNetworks/04-OwnFramework/README.md) | [Notatbok](./lessons/3-NeuralNetworks/04-OwnFramework/OwnFramework.ipynb) | [Lab](./lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md) |
| 05 | [Introduksjon til rammeverk (PyTorch/TensorFlow) og overtilpasning](./lessons/3-NeuralNetworks/05-Frameworks/README.md) | [PyTorch](./lessons/3-NeuralNetworks/05-Frameworks/IntroPyTorch.ipynb) / [Keras](./lessons/3-NeuralNetworks/05-Frameworks/IntroKeras.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/3-NeuralNetworks/05-Frameworks/lab/README.md) |
-| IV | [**Computer Vision**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Utforsk Computer Vision på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
-| 06 | [Introduksjon til Computer Vision. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notebook](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
-| 07 | [Konvolusjonale nevrale nettverk](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN-arkitekturer](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Lab](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
-| 08 | [Forhåndstrente nettverk og overføringslæring](./lessons/4-ComputerVision/08-TransferLearning/README.md) og [Treningstriks](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
-| 09 | [Autoenkodere og VAE-arkitektur](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
-| 10 | [Generative adversariell nettverk og kunstnerisk stiloverføring](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
+| IV | [**Datamaskinsyn**](./lessons/4-ComputerVision/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-computer-vision-pytorch/?WT.mc_id=academic-77998-cacaste) / [TensorFlow](https://docs.microsoft.com/learn/modules/intro-computer-vision-TensorFlow/?WT.mc_id=academic-77998-cacaste)| [Utforsk datamaskinsyn på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) |
+| 06 | [Introduksjon til datamaskinsyn. OpenCV](./lessons/4-ComputerVision/06-IntroCV/README.md) | [Notatbok](./lessons/4-ComputerVision/06-IntroCV/OpenCV.ipynb) | [Lab](./lessons/4-ComputerVision/06-IntroCV/lab/README.md) |
+| 07 | [Konvolusjonsnevrale nettverk](./lessons/4-ComputerVision/07-ConvNets/README.md) & [CNN-arkitekturer](./lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md) | [PyTorch](./lessons/4-ComputerVision/07-ConvNets/ConvNetsPyTorch.ipynb) /[TensorFlow](./lessons/4-ComputerVision/07-ConvNets/ConvNetsTF.ipynb) | [Lab](./lessons/4-ComputerVision/07-ConvNets/lab/README.md) |
+| 08 | [Forhåndstrente nettverk og overføringslæring](./lessons/4-ComputerVision/08-TransferLearning/README.md) og [Treningsknep](./lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md) | [PyTorch](./lessons/4-ComputerVision/08-TransferLearning/TransferLearningPyTorch.ipynb) / [TensorFlow](./lessons/3-NeuralNetworks/05-Frameworks/IntroKerasTF.ipynb) | [Lab](./lessons/4-ComputerVision/08-TransferLearning/lab/README.md) |
+| 09 | [Autoenkodere og VAEer](./lessons/4-ComputerVision/09-Autoencoders/README.md) | [PyTorch](./lessons/4-ComputerVision/09-Autoencoders/AutoEncodersPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/09-Autoencoders/AutoencodersTF.ipynb) | |
+| 10 | [Generative adversariale nettverk og kunstnerisk stiloverføring](./lessons/4-ComputerVision/10-GANs/README.md) | [PyTorch](./lessons/4-ComputerVision/10-GANs/GANPyTorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/10-GANs/GANTF.ipynb) | |
| 11 | [Objektdeteksjon](./lessons/4-ComputerVision/11-ObjectDetection/README.md) | [TensorFlow](./lessons/4-ComputerVision/11-ObjectDetection/ObjectDetection.ipynb) | [Lab](./lessons/4-ComputerVision/11-ObjectDetection/lab/README.md) |
| 12 | [Semantisk segmentering. U-Net](./lessons/4-ComputerVision/12-Segmentation/README.md) | [PyTorch](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationPytorch.ipynb) / [TensorFlow](./lessons/4-ComputerVision/12-Segmentation/SemanticSegmentationTF.ipynb) | |
| V | [**Naturlig språkbehandling**](./lessons/5-NLP/README.md) | [PyTorch](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-pytorch/?WT.mc_id=academic-77998-cacaste) /[TensorFlow](https://docs.microsoft.com/learn/modules/intro-natural-language-processing-TensorFlow/?WT.mc_id=academic-77998-cacaste) | [Utforsk naturlig språkbehandling på Microsoft Azure](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum)|
| 13 | [Tekstreprensentasjon. Bow/TF-IDF](./lessons/5-NLP/13-TextRep/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/13-TextRep/TextRepresentationTF.ipynb) | |
-| 14 | [Semantiske ordinnbeddings. Word2Vec og GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
-| 15 | [Språkmodellering. Trene dine egne innbeddings](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
+| 14 | [Semantiske ordinnpakninger. Word2Vec og GloVe](./lessons/5-NLP/14-Embeddings/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/14-Embeddings/EmbeddingsTF.ipynb) | |
+| 15 | [Språkmodellering. Trene dine egne innpakninger](./lessons/5-NLP/15-LanguageModeling/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-PyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/15-LanguageModeling/CBoW-TF.ipynb) | [Lab](./lessons/5-NLP/15-LanguageModeling/lab/README.md) |
| 16 | [Rekurrente nevrale nettverk](./lessons/5-NLP/16-RNN/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNPyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/16-RNN/RNNTF.ipynb) | |
| 17 | [Generative rekurrente nettverk](./lessons/5-NLP/17-GenerativeNetworks/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativePyTorch.ipynb) / [TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/17-GenerativeNetworks/GenerativeTF.ipynb) | [Lab](./lessons/5-NLP/17-GenerativeNetworks/lab/README.md) |
| 18 | [Transformers. BERT.](./lessons/5-NLP/18-Transformers/README.md) | [PyTorch](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersPyTorch.ipynb) /[TensorFlow](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/5-NLP/18-Transformers/TransformersTF.ipynb) | |
| 19 | [Navngitt enhetsgjenkjenning](./lessons/5-NLP/19-NER/README.md) | [TensorFlow](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/19-NER/NER-TF.ipynb) | [Lab](./lessons/5-NLP/19-NER/lab/README.md) |
-| 20 | [Store språkmodeller, promptprogrammering og få-skudd-oppgaver](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
+| 20 | [Store språkmodeller, promptprogrammering og få-skudd oppgaver](./lessons/5-NLP/20-LangModels/README.md) | [PyTorch](https://microsoft.github.io/AI-For-Beginners/lessons/5-NLP/20-LangModels/GPT-PyTorch.ipynb) | |
| VI | **Andre AI-teknikker** || |
-| 21 | [Genetiske algoritmer](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notebook](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
-| 22 | [Dyp forsterkningslæring](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) |
+| 21 | [Genetiske algoritmer](./lessons/6-Other/21-GeneticAlgorithms/README.md) | [Notatbok](./lessons/6-Other/21-GeneticAlgorithms/Genetic.ipynb) | |
+| 22 | [Dyp forsterkende læring](./lessons/6-Other/22-DeepRL/README.md) | [PyTorch](./lessons/6-Other/22-DeepRL/CartPole-RL-PyTorch.ipynb) /[TensorFlow](./lessons/6-Other/22-DeepRL/CartPole-RL-TF.ipynb) | [Lab](./lessons/6-Other/22-DeepRL/lab/README.md) |
| 23 | [Multi-agent systemer](./lessons/6-Other/23-MultiagentSystems/README.md) | | |
| VII | **AI-etikk** | | |
-| 24 | [AI-etikk og ansvarlig AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Ansvarlige AI-prinsipper](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
+| 24 | [AI-etikk og ansvarlig AI](./lessons/7-Ethics/README.md) | [Microsoft Learn: Prinsipper for ansvarlig AI](https://docs.microsoft.com/learn/paths/responsible-ai-business-principles/?WT.mc_id=academic-77998-cacaste) | |
| IX | **Ekstra** | | |
-| 25 | [Multimodale nettverk, CLIP og VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notebook](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
+| 25 | [Multimodale nettverk, CLIP og VQGAN](./lessons/X-Extras/X1-MultiModal/README.md) | [Notatbok](./lessons/X-Extras/X1-MultiModal/Clip.ipynb) | |
## Hver leksjon inneholder
-* Forhåndslesingsmateriale
-* Utførbare Jupyter Notebooks, som ofte er spesifikke for rammeverket (**PyTorch** eller **TensorFlow**). Den utførbare notatboken inneholder også mye teoretisk materiale, så for å forstå emnet må du gå igjennom minst én versjon av notatboken (enten PyTorch eller TensorFlow).
-* **Labber** tilgjengelig for noen temaer, som gir deg en mulighet til å prøve å anvende materialet du har lært på et spesifikt problem.
-* Noen seksjoner inneholder lenker til [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) moduler som dekker relaterte temaer.
+* Forlesningsmateriale
+* Kjørbare Jupyter Notebooks, som ofte er spesifikke for rammeverket (**PyTorch** eller **TensorFlow**). Den kjørbare notatboken inneholder også mye teoretisk materiale, så for å forstå emnet må du gå gjennom minst én versjon av notatboken (enten PyTorch eller TensorFlow).
+* **Laboratorier** tilgjengelig for noen emner, som gir deg mulighet til å prøve å anvende materialet du har lært på et spesifikt problem.
+* Noen seksjoner inneholder lenker til [**MS Learn**](https://learn.microsoft.com/en-us/collections/7w28iy2xrqzdj0?WT.mc_id=academic-77998-bethanycheum) moduler som dekker relaterte emner.
## Komme i gang
-### 🎯 Ny til AI? Start her!
+### 🎯 Ny i AI? Start her!
-Hvis du er helt ny til AI og ønsker raske, praktiske eksempler, sjekk ut våre [**Begynnervennlige eksempler**](./examples/README.md)! Disse inkluderer:
+Hvis du er helt ny til AI og ønsker raske, praktiske eksempler, sjekk ut våre [**Nybegynnervennlige eksempler**](./examples/README.md)! Disse inkluderer:
-- 🌟 **Hello AI World** - Ditt første AI-program (mønster-gjenkjenning)
+- 🌟 **Hello AI World** - Ditt første AI-program (mønster- gjenkjenning)
- 🧠 **Enkelt nevralt nettverk** - Bygg et nevralt nettverk fra bunnen av
-- 🖼️ **Bildklassifiserer** - Klassifiser bilder med detaljerte kommentarer
-- 💬 **Tekststemning** - Analyser positiv/negativ tekst
-Disse eksemplene er laget for å hjelpe deg å forstå AI-konsepter før du dykker inn i hele læreplanen.
+- 🖼️ **Bildeklassifisering** - Klassifiser bilder med detaljerte kommentarer
+- 💬 **Tekstfølelse** - Analyser positiv/negativ tekst
-### 📚 Full Læreplanoppsett
+Disse eksemplene er laget for å hjelpe deg å forstå AI-konsepter før du går videre til hele pensumet.
-- Vi har laget en [oppsett-leksjon](./lessons/0-course-setup/setup.md) for å hjelpe deg med å sette opp utviklingsmiljøet ditt. - For lærere har vi også laget en [læreplansoppsett-leksjon](./lessons/0-course-setup/for-teachers.md)!
-- Hvordan [kjøre koden i VSCode eller en Codespace](./lessons/0-course-setup/how-to-run.md)
+### 📚 Fullt pensumoppsett
+
+- Vi har laget en [oppsett-leksjon](./lessons/0-course-setup/setup.md) for å hjelpe deg med å sette opp utviklingsmiljøet ditt. - For lærere har vi også laget en [pensumoppsett-leksjon](./lessons/0-course-setup/for-teachers.md)!
+- Hvordan [Kjøre koden i VSCode eller en Codespace](./lessons/0-course-setup/how-to-run.md)
Følg disse trinnene:
-Fork repositoryet: Klikk på "Fork" knappen øverst til høyre på denne siden.
+Fork depotet: Klikk på "Fork" knappen oppe til høyre på denne siden.
-Klon repositoryet: `git clone https://github.com/microsoft/AI-For-Beginners.git`
+Klon depotet: `git clone https://github.com/microsoft/AI-For-Beginners.git`
-Ikke glem å stjerne (🌟) dette repoet for å finne det lettere senere.
+Ikke glem å gi dette repoet en stjerne (🌟) for å finne det lettere senere.
## Møt andre lærende
-Bli med på vår [offisielle AI Discord-server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) for å møte og nettverke med andre som tar dette kurset og få støtte.
+Bli med i vår [offisielle AI Discord-server](https://aka.ms/genai-discord?WT.mc_id=academic-105485-bethanycheum) for å møte og nettverke med andre som tar dette kurset og få støtte.
-Hvis du har produktfeedback eller spørsmål mens du bygger, besøk vår [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
+Hvis du har produktinnspill eller spørsmål mens du bygger, besøk vår [Azure AI Foundry Developer Forum](https://aka.ms/foundry/forum)
-## Quizzer
+## Quizzer
-> **En merknad om quizzer**: Alle quizzer ligger i Quiz-app mappen i etc\quiz-app, eller [Online her](https://ff-quizzes.netlify.app/) De er lenket fra leksjonene, quiz-appen kan kjøres lokalt eller distribueres til Azure; følg instruksjonene i `quiz-app` mappen. De lokaliseres gradvis.
+> **En merknad om quizzer**: Alle quizzer ligger i Quiz-app-mappen i etc\quiz-app, eller [Online her](https://ff-quizzes.netlify.app/) De er linket fra leksjonene, quiz-appen kan kjøres lokalt eller distribueres til Azure; følg instruksjonen i `quiz-app`-mappen. De blir gradvis lokalisert.
-## Hjelp ønskes
+## Trenger hjelp
-Har du forslag eller funnet stave- eller kodefeil? Opprett en issue eller pull request.
+Har du forslag eller funnet skrivefeil eller kodefeil? Opprett en sak eller send en pull request.
-## Spesiell takk
+## Spesielle takk
-* **✍️ Hovedforfatter:** [Dmitry Soshnikov](http://soshnikov.com), PhD
-* **🔥 Redaktør:** [Jen Looper](https://twitter.com/jenlooper), PhD
-* **🎨 Sketchnote-illustratør:** [Tomomi Imura](https://twitter.com/girlie_mac)
-* **✅ Quiz-skaper:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
+* **✍️ Hovedforfatter:** [Dmitry Soshnikov](http://soshnikov.com), PhD
+* **🔥 Redaktør:** [Jen Looper](https://twitter.com/jenlooper), PhD
+* **🎨 Sketchnote-illustratør:** [Tomomi Imura](https://twitter.com/girlie_mac)
+* **✅ Quiz-skaper:** [Lateefah Bello](https://github.com/CinnamonXI), [MLSA](https://studentambassadors.microsoft.com/)
* **🙏 Kjernebidragsytere:** [Evgenii Pishchik](https://github.com/Pe4enIks)
-## Andre læreplaner
+## Andre pensum
-Teamet vårt lager andre læreplaner! Sjekk ut:
+Vårt team lager andre pensum! Sjekk ut:
### LangChain
-[](https://aka.ms/langchain4j-for-beginners)
+[](https://aka.ms/langchain4j-for-beginners)
[](https://aka.ms/langchainjs-for-beginners?WT.mc_id=m365-94501-dwahlin)
---
### Azure / Edge / MCP / Agenter
-[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/AZD-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/edgeai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mcp-for-beginners?WT.mc_id=academic-105485-koreyst)
[](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst)
---
-
-### Generativ AI Serie
-[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
-[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
-[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
+
+### Generativ AI-serie
+[](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst)
+[-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA)](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst)
+[-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC)](https://github.com/microsoft/generative-ai-for-beginners-java?WT.mc_id=academic-105485-koreyst)
[-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9)](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst)
---
-
-### Kjerneopplæring
-[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
-[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
-[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
+
+### Kjerneprogrammering
+[](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/Security-101?WT.mc_id=academic-96948-sayoung)
+[](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst)
+[](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst)
[](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst)
---
-
-### Copilot Serie
-[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
-[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
+
+### Copilot-serie
+[](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst)
+[](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst)
## Få hjelp
-Hvis du står fast eller har spørsmål om å bygge AI-apper. Bli med andre lærende og erfarne utviklere i diskusjoner om MCP. Det er et støttende fellesskap hvor spørsmål er velkomne og kunnskap deles fritt.
+Hvis du sitter fast eller har spørsmål om å bygge AI-apper. Bli med på diskusjoner med andre lærende og erfarne utviklere om MCP. Det er et støttende fellesskap hvor spørsmål er velkomne og kunnskap deles fritt.
[](https://discord.gg/nTYy5BXMWG)
-Hvis du har produktfeedback eller feil mens du bygger, besøk:
+Hvis du har produktinnspill eller feil mens du bygger, besøk:
[](https://aka.ms/foundry/forum)
---
-**Ansvarsfraskrivelse**:
-Dette dokumentet er oversatt ved hjelp av AI-oversettelsestjenesten [Co-op Translator](https://github.com/Azure/co-op-translator). Selv om vi streber etter nøyaktighet, vennligst vær oppmerksom på at automatiske oversettelser kan inneholde feil eller unøyaktigheter. Det opprinnelige dokumentet på dets opprinnelige språk bør anses som den autoritative kilden. For kritisk informasjon anbefales profesjonell menneskelig oversettelse. Vi er ikke ansvarlige for eventuelle misforståelser eller feiltolkninger som oppstår ved bruk av denne oversettelsen.
+**Fraskrivelse**:
+Dette dokumentet er oversatt ved hjelp av AI-oversettelsestjenesten [Co-op Translator](https://github.com/Azure/co-op-translator). Selv om vi streber etter nøyaktighet, vennligst vær oppmerksom på at automatiserte oversettelser kan inneholde feil eller unøyaktigheter. Det originale dokumentet på det opprinnelige språket skal anses som den autoritative kilden. For kritisk informasjon anbefales profesjonell menneskelig oversettelse. Vi er ikke ansvarlige for eventuelle misforståelser eller feiltolkninger som oppstår ved bruk av denne oversettelsen.
\ No newline at end of file
diff --git a/translations/no/SECURITY.md b/translations/no/SECURITY.md
index 025f7a23..fb375bb5 100644
--- a/translations/no/SECURITY.md
+++ b/translations/no/SECURITY.md
@@ -1,12 +1,3 @@
-
## Sikkerhet
Microsoft tar sikkerheten til våre programvareprodukter og tjenester på alvor, inkludert alle kildekoderepositorier som administreres gjennom våre GitHub-organisasjoner, som inkluderer [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin) og [våre GitHub-organisasjoner](https://opensource.microsoft.com/).
diff --git a/translations/no/etc/CODE_OF_CONDUCT.md b/translations/no/etc/CODE_OF_CONDUCT.md
index 897c7d5f..7d676932 100644
--- a/translations/no/etc/CODE_OF_CONDUCT.md
+++ b/translations/no/etc/CODE_OF_CONDUCT.md
@@ -1,12 +1,3 @@
-
# Microsoft Open Source Code of Conduct
Dette prosjektet har tatt i bruk [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
diff --git a/translations/no/etc/CONTRIBUTING.md b/translations/no/etc/CONTRIBUTING.md
index 01ccb823..2f4dc076 100644
--- a/translations/no/etc/CONTRIBUTING.md
+++ b/translations/no/etc/CONTRIBUTING.md
@@ -1,12 +1,3 @@
-
# Bidra
Dette prosjektet ønsker bidrag og forslag velkommen. De fleste bidrag krever at du
diff --git a/translations/no/etc/Mindmap.md b/translations/no/etc/Mindmap.md
index cba54e88..f0b82351 100644
--- a/translations/no/etc/Mindmap.md
+++ b/translations/no/etc/Mindmap.md
@@ -1,12 +1,3 @@
-
# AI
## [Introduksjon til AI](https://github.com/microsoft/AI-For-Beginners/blob/main/lessons/1-Intro/README.md)
diff --git a/translations/no/etc/SUPPORT.md b/translations/no/etc/SUPPORT.md
index 3bef07b0..d207b0ea 100644
--- a/translations/no/etc/SUPPORT.md
+++ b/translations/no/etc/SUPPORT.md
@@ -1,12 +1,3 @@
-
# Støtte
## Hvordan rapportere problemer og få hjelp
diff --git a/translations/no/etc/TRANSLATIONS.md b/translations/no/etc/TRANSLATIONS.md
index 120e3a83..6194b1ca 100644
--- a/translations/no/etc/TRANSLATIONS.md
+++ b/translations/no/etc/TRANSLATIONS.md
@@ -1,12 +1,3 @@
-
# Bidra ved å oversette leksjoner
Vi ønsker oversettelser av leksjonene i dette pensumet velkommen!
diff --git a/translations/no/etc/quiz-app/README.md b/translations/no/etc/quiz-app/README.md
index bdd192a6..703adbd4 100644
--- a/translations/no/etc/quiz-app/README.md
+++ b/translations/no/etc/quiz-app/README.md
@@ -1,12 +1,3 @@
-
# Quizzer
Disse quizene er forhånds- og etterforelesningsquizene for AI-pensumet på https://aka.ms/ai-beginners
diff --git a/translations/no/examples/README.md b/translations/no/examples/README.md
index 5612ae65..3d2dc7fe 100644
--- a/translations/no/examples/README.md
+++ b/translations/no/examples/README.md
@@ -1,12 +1,3 @@
-
# Nybegynnervennlige AI-eksempler
Velkommen! Denne katalogen inneholder enkle, frittstående eksempler som hjelper deg med å komme i gang med AI og maskinlæring. Hvert eksempel er laget for å være nybegynnervennlig med detaljerte kommentarer og trinnvise forklaringer.
diff --git a/translations/no/lessons/0-course-setup/for-teachers.md b/translations/no/lessons/0-course-setup/for-teachers.md
index 59b6a95c..d7a23188 100644
--- a/translations/no/lessons/0-course-setup/for-teachers.md
+++ b/translations/no/lessons/0-course-setup/for-teachers.md
@@ -1,12 +1,3 @@
-
# For lærere
Ønsker du å bruke dette pensumet i klasserommet ditt? Vær så god!
diff --git a/translations/no/lessons/0-course-setup/how-to-run.md b/translations/no/lessons/0-course-setup/how-to-run.md
index faf854d6..cb44d5aa 100644
--- a/translations/no/lessons/0-course-setup/how-to-run.md
+++ b/translations/no/lessons/0-course-setup/how-to-run.md
@@ -1,12 +1,3 @@
-
# Hvordan kjøre koden
Dette pensumet inneholder mange kjørbare eksempler og laboratorier som du vil kjøre. For å gjøre dette trenger du muligheten til å kjøre Python-kode i Jupyter Notebooks som følger med i dette pensumet. Du har flere alternativer for å kjøre koden:
diff --git a/translations/no/lessons/0-course-setup/setup.md b/translations/no/lessons/0-course-setup/setup.md
index 9d2e4231..9808a3eb 100644
--- a/translations/no/lessons/0-course-setup/setup.md
+++ b/translations/no/lessons/0-course-setup/setup.md
@@ -1,12 +1,3 @@
-
# Komme i gang med dette pensumet
## Er du student?
diff --git a/translations/no/lessons/1-Intro/README.md b/translations/no/lessons/1-Intro/README.md
index 5eab5462..372c5701 100644
--- a/translations/no/lessons/1-Intro/README.md
+++ b/translations/no/lessons/1-Intro/README.md
@@ -1,12 +1,3 @@
-
# Introduksjon til AI
diff --git a/translations/no/lessons/1-Intro/assignment.md b/translations/no/lessons/1-Intro/assignment.md
index 9e590da3..c751584c 100644
--- a/translations/no/lessons/1-Intro/assignment.md
+++ b/translations/no/lessons/1-Intro/assignment.md
@@ -1,12 +1,3 @@
-
# Spilljam
Spill er et område som har blitt sterkt påvirket av utviklingen innen AI og maskinlæring. I denne oppgaven skal du skrive en kort tekst om et spill du liker som har blitt påvirket av AI-utviklingen. Det bør være et spill som er gammelt nok til å ha blitt påvirket av flere typer databehandlingssystemer. Et godt eksempel er sjakk eller Go, men du kan også se på videospill som Pong eller Pac-Man. Skriv et essay som diskuterer spillets fortid, nåtid og AI-fremtid.
diff --git a/translations/no/lessons/2-Symbolic/README.md b/translations/no/lessons/2-Symbolic/README.md
index dd5aced2..f505ab18 100644
--- a/translations/no/lessons/2-Symbolic/README.md
+++ b/translations/no/lessons/2-Symbolic/README.md
@@ -1,15 +1,6 @@
-
# Kunnskapsrepresentasjon og Ekspertsystemer
-
+
> Sketchnote av [Tomomi Imura](https://twitter.com/girlie_mac)
@@ -41,7 +32,7 @@ Ofte definerer vi ikke kunnskap strengt, men vi plasserer den i forhold til andr
Dermed er problemet med **kunnskapsrepresentasjon** å finne en effektiv måte å representere kunnskap inne i en datamaskin i form av data, slik at den kan brukes automatisk. Dette kan sees som et spektrum:
-
+
> Bilde av [Dmitry Soshnikov](http://soshnikov.com)
@@ -94,7 +85,7 @@ Blokk-syntaks | Innrykk | | |
En av de tidlige suksessene innen symbolsk KI var såkalte **ekspertsystemer** – datasystemer som var designet for å opptre som eksperter i et begrenset problemområde. De baserte seg på en **kunnskapsbase** hentet fra en eller flere menneskelige eksperter, og de inneholdt en **begrunnelsesmotor** som utførte resonnering på toppen av dette.
- | 
+ | 
---------------------------------------------|------------------------------------------------
Forenklet struktur av menneskelig nervesystem | Arkitektur for et kunnskapsbasert system
@@ -106,7 +97,7 @@ Ekspertsystemer er bygd som det menneskelige resonnementssystemet, som inneholde
Som eksempel kan vi se på følgende ekspertsystem for å bestemme et dyr basert på dets fysiske egenskaper:
-
+
> Bilde av [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/no/lessons/2-Symbolic/assignment.md b/translations/no/lessons/2-Symbolic/assignment.md
index 0eef2cb6..d515db54 100644
--- a/translations/no/lessons/2-Symbolic/assignment.md
+++ b/translations/no/lessons/2-Symbolic/assignment.md
@@ -1,12 +1,3 @@
-
# Bygg en ontologi
Å bygge en kunnskapsbase handler om å kategorisere en modell som representerer fakta om et emne. Velg et emne - som en person, et sted eller en ting - og bygg deretter en modell av det emnet. Bruk noen av teknikkene og strategiene for modellbygging som er beskrevet i denne leksjonen. Et eksempel kan være å lage en ontologi for en stue med møbler, lys og så videre. Hvordan skiller stuen seg fra kjøkkenet? Badet? Hvordan vet du at det er en stue og ikke en spisestue? Bruk [Protégé](https://protege.stanford.edu/) til å bygge din ontologi.
diff --git a/translations/no/lessons/3-NeuralNetworks/03-Perceptron/README.md b/translations/no/lessons/3-NeuralNetworks/03-Perceptron/README.md
index d4e87c9c..5bfe8741 100644
--- a/translations/no/lessons/3-NeuralNetworks/03-Perceptron/README.md
+++ b/translations/no/lessons/3-NeuralNetworks/03-Perceptron/README.md
@@ -1,12 +1,3 @@
-
# Introduksjon til nevrale nettverk: Perceptron
## [Quiz før forelesning](https://ff-quizzes.netlify.app/en/ai/quiz/5)
@@ -15,7 +6,7 @@ En av de første forsøkene på å implementere noe som ligner på et moderne ne
| | |
|--------------|-----------|
-| | |
+|
| 
|
> Bilder [fra Wikipedia](https://en.wikipedia.org/wiki/Perceptron)
@@ -34,7 +25,7 @@ y(x) = f(wTx)
hvor f er en stegaktiveringsfunksjon
-
+
## Trening av perceptron
diff --git a/translations/no/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md b/translations/no/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
index 43173e18..b177ba8c 100644
--- a/translations/no/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
+++ b/translations/no/lessons/3-NeuralNetworks/03-Perceptron/lab/README.md
@@ -1,12 +1,3 @@
-
# Multi-klasseklassifisering med Perceptron
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/README.md b/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/README.md
index 9bbe3866..f33f0eef 100644
--- a/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/README.md
+++ b/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/README.md
@@ -1,12 +1,3 @@
-
# Introduksjon til nevrale nettverk. Multi-lags perceptron
I forrige seksjon lærte du om den enkleste modellen for nevrale nettverk – en én-lags perceptron, en lineær to-klasse klassifiseringsmodell.
@@ -65,7 +56,7 @@ Gradientnedstigningsalgoritmen vil forbli den samme, men det vil være mer utfor
Merk at den venstre delen av alle disse uttrykkene er den samme, og dermed kan vi effektivt beregne derivertene ved å starte fra tapfunksjonen og gå "bakover" gjennom beregningsgrafen. Dermed kalles metoden for trening av en multi-lags perceptron **backpropagation**, eller 'backprop'.
-
+
> TODO: bildehenvisning
diff --git a/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md b/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
index 078874bc..29591ef2 100644
--- a/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
+++ b/translations/no/lessons/3-NeuralNetworks/04-OwnFramework/lab/README.md
@@ -1,12 +1,3 @@
-
# MNIST-klassifisering med vårt eget rammeverk
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/3-NeuralNetworks/05-Frameworks/README.md b/translations/no/lessons/3-NeuralNetworks/05-Frameworks/README.md
index 7b08afa9..b271e81f 100644
--- a/translations/no/lessons/3-NeuralNetworks/05-Frameworks/README.md
+++ b/translations/no/lessons/3-NeuralNetworks/05-Frameworks/README.md
@@ -1,12 +1,3 @@
-
# Rammeverk for nevrale nettverk
Som vi allerede har lært, for å kunne trene nevrale nettverk effektivt må vi gjøre to ting:
diff --git a/translations/no/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md b/translations/no/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
index a70794cd..76ac470f 100644
--- a/translations/no/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
+++ b/translations/no/lessons/3-NeuralNetworks/05-Frameworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Klassifisering med PyTorch/TensorFlow
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/3-NeuralNetworks/README.md b/translations/no/lessons/3-NeuralNetworks/README.md
index ff17a345..bbce3b9f 100644
--- a/translations/no/lessons/3-NeuralNetworks/README.md
+++ b/translations/no/lessons/3-NeuralNetworks/README.md
@@ -1,12 +1,3 @@
-
# Introduksjon til nevrale nettverk
diff --git a/translations/no/lessons/4-ComputerVision/06-IntroCV/README.md b/translations/no/lessons/4-ComputerVision/06-IntroCV/README.md
index fd627c0a..43252a62 100644
--- a/translations/no/lessons/4-ComputerVision/06-IntroCV/README.md
+++ b/translations/no/lessons/4-ComputerVision/06-IntroCV/README.md
@@ -1,12 +1,3 @@
-
# Introduksjon til datamaskinsyn
[Datamaskinsyn](https://wikipedia.org/wiki/Computer_vision) er et fagområde som har som mål å gi datamaskiner en høyere forståelse av digitale bilder. Dette er en ganske bred definisjon, fordi *forståelse* kan bety mange forskjellige ting, inkludert å finne et objekt på et bilde (**objektdeteksjon**), forstå hva som skjer (**hendelsesdeteksjon**), beskrive et bilde med tekst, eller rekonstruere en scene i 3D. Det finnes også spesielle oppgaver knyttet til bilder av mennesker: alders- og følelsesestimering, ansiktsdeteksjon og identifikasjon, samt 3D-posisjonsestimering, for å nevne noen.
@@ -115,7 +106,7 @@ Les mer om optisk flyt [i denne flotte veiledningen](https://learnopencv.com/opt
I denne laben skal du ta en video med enkle bevegelser, og målet ditt er å trekke ut opp/ned/venstre/høyre bevegelser ved hjelp av optisk flyt.
-
+
---
diff --git a/translations/no/lessons/4-ComputerVision/06-IntroCV/lab/README.md b/translations/no/lessons/4-ComputerVision/06-IntroCV/lab/README.md
index 802f2049..abd4f44b 100644
--- a/translations/no/lessons/4-ComputerVision/06-IntroCV/lab/README.md
+++ b/translations/no/lessons/4-ComputerVision/06-IntroCV/lab/README.md
@@ -1,12 +1,3 @@
-
# Oppdage bevegelser ved hjelp av optisk flyt
Laboppgave fra [AI for Beginners Curriculum](https://aka.ms/ai-beginners).
diff --git a/translations/no/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md b/translations/no/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
index 32840dda..609c9ff6 100644
--- a/translations/no/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
+++ b/translations/no/lessons/4-ComputerVision/07-ConvNets/CNN_Architectures.md
@@ -1,12 +1,3 @@
-
# Velkjente CNN-arkitekturer
### VGG-16
@@ -25,7 +16,7 @@ Som du kan se, følger VGG en tradisjonell pyramidearkitektur, som er en sekvens
ResNet er en familie av modeller foreslått av Microsoft Research i 2015. Hovedideen bak ResNet er å bruke **residualblokker**:
-
+
> Bilde fra [denne artikkelen](https://arxiv.org/pdf/1512.03385.pdf)
@@ -37,7 +28,7 @@ Du kan også tenke på dette nettverket som i stand til å justere kompleksitete
Google Inception-arkitekturen tar denne ideen et steg videre og bygger hvert nettverkslag som en kombinasjon av flere forskjellige veier:
-
+
> Bilde fra [Researchgate](https://www.researchgate.net/figure/Inception-module-with-dimension-reductions-left-and-schema-for-Inception-ResNet-v1_fig2_355547454)
diff --git a/translations/no/lessons/4-ComputerVision/07-ConvNets/README.md b/translations/no/lessons/4-ComputerVision/07-ConvNets/README.md
index f01067aa..e8e98bfc 100644
--- a/translations/no/lessons/4-ComputerVision/07-ConvNets/README.md
+++ b/translations/no/lessons/4-ComputerVision/07-ConvNets/README.md
@@ -1,12 +1,3 @@
-
# Konvolusjonelle Nevrale Nettverk
Vi har tidligere sett at nevrale nettverk er ganske gode til å håndtere bilder, og til og med en ett-lags perceptron kan gjenkjenne håndskrevne sifre fra MNIST-datasettet med rimelig nøyaktighet. MNIST-datasettet er imidlertid veldig spesielt, og alle sifrene er sentrert i bildet, noe som gjør oppgaven enklere.
@@ -24,7 +15,7 @@ For å trekke ut mønstre, vil vi bruke begrepet **konvolusjonsfiltre**. Som du
For eksempel, hvis vi bruker 3x3 vertikale og horisontale kantfiltre på MNIST-sifrene, kan vi få fremhevinger (f.eks. høye verdier) der det er vertikale og horisontale kanter i vårt originale bilde. Dermed kan disse to filtrene brukes til å "se etter" kanter. På samme måte kan vi designe forskjellige filtre for å se etter andre lavnivåmønstre:
-
+
> Bilde av [Leung-Malik Filter Bank](https://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html)
diff --git a/translations/no/lessons/4-ComputerVision/07-ConvNets/lab/README.md b/translations/no/lessons/4-ComputerVision/07-ConvNets/lab/README.md
index 6b50467e..fbe2f548 100644
--- a/translations/no/lessons/4-ComputerVision/07-ConvNets/lab/README.md
+++ b/translations/no/lessons/4-ComputerVision/07-ConvNets/lab/README.md
@@ -1,12 +1,3 @@
-
# Klassifisering av kjæledyrs ansikter
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/4-ComputerVision/08-TransferLearning/README.md b/translations/no/lessons/4-ComputerVision/08-TransferLearning/README.md
index adc01564..e45fd76f 100644
--- a/translations/no/lessons/4-ComputerVision/08-TransferLearning/README.md
+++ b/translations/no/lessons/4-ComputerVision/08-TransferLearning/README.md
@@ -1,12 +1,3 @@
-
# Forhåndstrente nettverk og overføringslæring
Å trene CNN-er kan ta mye tid, og det kreves store mengder data for denne oppgaven. Mye av tiden brukes imidlertid på å lære de beste lavnivåfiltrene som et nettverk kan bruke for å trekke ut mønstre fra bilder. Et naturlig spørsmål oppstår: Kan vi bruke et nevralt nettverk som er trent på ett datasett og tilpasse det til å klassifisere andre bilder uten å måtte gjennomføre en full treningsprosess?
diff --git a/translations/no/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md b/translations/no/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
index 9b452dae..63ad6490 100644
--- a/translations/no/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
+++ b/translations/no/lessons/4-ComputerVision/08-TransferLearning/TrainingTricks.md
@@ -1,12 +1,3 @@
-
# Triks for Trening av Dype Nevrale Nettverk
Etter hvert som nevrale nettverk blir dypere, blir treningsprosessen stadig mer utfordrende. Et stort problem er de såkalte [forsvinnende gradientene](https://en.wikipedia.org/wiki/Vanishing_gradient_problem) eller [eksploderende gradientene](https://deepai.org/machine-learning-glossary-and-terms/exploding-gradient-problem#:~:text=Exploding%20gradients%20are%20a%20problem,updates%20are%20small%20and%20controlled.). [Denne artikkelen](https://towardsdatascience.com/the-vanishing-exploding-gradient-problem-in-deep-neural-networks-191358470c11) gir en god introduksjon til disse problemene.
diff --git a/translations/no/lessons/4-ComputerVision/08-TransferLearning/lab/README.md b/translations/no/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
index 7383db7e..5645a0a2 100644
--- a/translations/no/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
+++ b/translations/no/lessons/4-ComputerVision/08-TransferLearning/lab/README.md
@@ -1,12 +1,3 @@
-
# Klassifisering av Oxford Pets ved bruk av Transfer Learning
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/4-ComputerVision/09-Autoencoders/README.md b/translations/no/lessons/4-ComputerVision/09-Autoencoders/README.md
index cd88734d..e65e07f4 100644
--- a/translations/no/lessons/4-ComputerVision/09-Autoencoders/README.md
+++ b/translations/no/lessons/4-ComputerVision/09-Autoencoders/README.md
@@ -1,12 +1,3 @@
-
# Autoencodere
Når vi trener CNN-er, er en av utfordringene at vi trenger mye merket data. Når det gjelder bildeklassifisering, må vi dele bilder inn i ulike klasser, noe som krever manuell innsats.
@@ -46,7 +37,7 @@ Oppsummert:
* Vi tar en prøvevektor `sample` fra distribusjonen N(zmean,exp(zlog\_sigma))
* Decoder prøver å dekode det originale bildet ved å bruke `sample` som input-vektor
-
+ 
> Bilde fra [denne bloggposten](https://ijdykeman.github.io/ml/2016/12/21/cvae.html) av Isaak Dykeman
@@ -57,13 +48,13 @@ Variasjonelle autoencodere bruker en kompleks tapsfunksjon som består av to del
En viktig fordel med VAE-er er at de lar oss generere nye bilder relativt enkelt, fordi vi vet hvilken distribusjon vi skal ta latente vektorer fra. For eksempel, hvis vi trener VAE med 2D latente vektorer på MNIST, kan vi deretter variere komponentene i den latente vektoren for å få ulike sifre:
-
+
> Bilde av [Dmitry Soshnikov](http://soshnikov.com)
Legg merke til hvordan bildene glir over i hverandre, ettersom vi begynner å ta latente vektorer fra ulike deler av det latente parameterrommet. Vi kan også visualisere dette rommet i 2D:
-
+
> Bilde av [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/no/lessons/4-ComputerVision/10-GANs/README.md b/translations/no/lessons/4-ComputerVision/10-GANs/README.md
index 18a59fe5..ca2e72db 100644
--- a/translations/no/lessons/4-ComputerVision/10-GANs/README.md
+++ b/translations/no/lessons/4-ComputerVision/10-GANs/README.md
@@ -1,12 +1,3 @@
-
# Generative Adversarial Networks
I forrige seksjon lærte vi om **generative modeller**: modeller som kan generere nye bilder som ligner på de i treningsdatasettet. VAE var et godt eksempel på en generativ modell.
@@ -17,7 +8,7 @@ Men hvis vi prøver å generere noe virkelig meningsfullt, som et maleri med rim
Hovedideen med en GAN er å ha to nevrale nettverk som trenes mot hverandre:
-
+
> Bilde av [Dmitry Soshnikov](http://soshnikov.com)
@@ -41,7 +32,7 @@ En generator er litt mer komplisert. Du kan se på den som en omvendt discrimina
> ✅ Fordi konvolusjonslaget implementeres som et lineært filter som beveger seg over bildet, er dekonvolusjon i hovedsak lik konvolusjon og kan implementeres med samme laglogikk.
-
+
> Bilde av [Dmitry Soshnikov](http://soshnikov.com)
diff --git a/translations/no/lessons/4-ComputerVision/11-ObjectDetection/README.md b/translations/no/lessons/4-ComputerVision/11-ObjectDetection/README.md
index fa31b8ca..74061be1 100644
--- a/translations/no/lessons/4-ComputerVision/11-ObjectDetection/README.md
+++ b/translations/no/lessons/4-ComputerVision/11-ObjectDetection/README.md
@@ -1,12 +1,3 @@
-
# Objektgjenkjenning
Bildklassifiseringsmodellene vi har jobbet med så langt tar et bilde og gir et kategorisk resultat, som klassen 'nummer' i et MNIST-problem. Men i mange tilfeller ønsker vi ikke bare å vite at et bilde viser objekter – vi vil også kunne bestemme deres nøyaktige plassering. Dette er nettopp poenget med **objektgjenkjenning**.
diff --git a/translations/no/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md b/translations/no/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
index 087605ea..86d63a88 100644
--- a/translations/no/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
+++ b/translations/no/lessons/4-ComputerVision/11-ObjectDetection/lab/README.md
@@ -1,12 +1,3 @@
-
# Hodedeteksjon ved bruk av Hollywood Heads Dataset
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/4-ComputerVision/12-Segmentation/README.md b/translations/no/lessons/4-ComputerVision/12-Segmentation/README.md
index 16f1a7d3..970bd666 100644
--- a/translations/no/lessons/4-ComputerVision/12-Segmentation/README.md
+++ b/translations/no/lessons/4-ComputerVision/12-Segmentation/README.md
@@ -1,12 +1,3 @@
-
# Segmentering
Vi har tidligere lært om objektdeteksjon, som lar oss lokalisere objekter i et bilde ved å forutsi deres *bounding boxes*. Men for noen oppgaver trenger vi ikke bare bounding boxes, men også mer presis objektlokalisering. Denne oppgaven kalles **segmentering**.
@@ -20,7 +11,7 @@ Segmentering kan sees på som **pikselklassifisering**, der vi for **hver** piks
For instanssegmentering er disse sauene forskjellige objekter, men for semantisk segmentering representeres alle sauene av én klasse.
-
+
> Bilde fra [denne bloggposten](https://nirmalamurali.medium.com/image-classification-vs-semantic-segmentation-vs-instance-segmentation-625c33a08d50)
@@ -29,7 +20,7 @@ Det finnes ulike nevrale arkitekturer for segmentering, men de har alle samme st
* **Encoder** trekker ut funksjoner fra inngangsbilde.
* **Decoder** transformerer disse funksjonene til **maske-bildet**, med samme størrelse og antall kanaler som tilsvarer antall klasser.
-
+
> Bilde fra [denne publikasjonen](https://arxiv.org/pdf/2001.05566.pdf)
@@ -43,7 +34,7 @@ I denne leksjonen skal vi se segmentering i praksis ved å trene et nettverk til
> ✅ Denne teknikken er spesielt egnet for denne typen medisinsk bildediagnostikk, men hvilke andre virkelige applikasjoner kan du se for deg?
-
+
> Bilde fra PH2-databasen
diff --git a/translations/no/lessons/4-ComputerVision/12-Segmentation/lab/README.md b/translations/no/lessons/4-ComputerVision/12-Segmentation/lab/README.md
index 0e79eec3..969e688c 100644
--- a/translations/no/lessons/4-ComputerVision/12-Segmentation/lab/README.md
+++ b/translations/no/lessons/4-ComputerVision/12-Segmentation/lab/README.md
@@ -1,12 +1,3 @@
-
# Segmentering av menneskekroppen
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/4-ComputerVision/README.md b/translations/no/lessons/4-ComputerVision/README.md
index 2877b89f..5ab36d0e 100644
--- a/translations/no/lessons/4-ComputerVision/README.md
+++ b/translations/no/lessons/4-ComputerVision/README.md
@@ -1,12 +1,3 @@
-
# Datamaskinsyn
diff --git a/translations/no/lessons/5-NLP/13-TextRep/README.md b/translations/no/lessons/5-NLP/13-TextRep/README.md
index 662b688e..6a1a4c31 100644
--- a/translations/no/lessons/5-NLP/13-TextRep/README.md
+++ b/translations/no/lessons/5-NLP/13-TextRep/README.md
@@ -1,12 +1,3 @@
-
# Representere tekst som tensorer
## [Quiz før forelesning](https://ff-quizzes.netlify.app/en/ai/quiz/25)
@@ -25,7 +16,7 @@ Målet vårt vil være å klassifisere nyhetsartikkelen i en av kategoriene base
Hvis vi ønsker å løse oppgaver innen Natural Language Processing (NLP) med nevrale nettverk, trenger vi en måte å representere tekst som tensorer. Datamaskiner representerer allerede teksttegn som tall som kartlegger til fonter på skjermen din ved hjelp av kodinger som ASCII eller UTF-8.
-
+
> [Bildekilde](https://www.seobility.net/en/wiki/ASCII)
@@ -48,7 +39,7 @@ I noen tilfeller kan vi vurdere å bruke tri-grams -- kombinasjoner av tre ord -
Når vi løser oppgaver som tekstklassifisering, må vi kunne representere tekst med én vektor av fast størrelse, som vi vil bruke som input til den endelige tette klassifisereren. En av de enkleste måtene å gjøre dette på er å kombinere alle individuelle ordrepresentasjoner, f.eks. ved å legge dem sammen. Hvis vi legger sammen one-hot encodingene av hvert ord, ender vi opp med en frekvensvektor som viser hvor mange ganger hvert ord vises i teksten. En slik representasjon av tekst kalles **bag of words** (BoW).
-
+
> Bilde av forfatteren
diff --git a/translations/no/lessons/5-NLP/13-TextRep/assignment.md b/translations/no/lessons/5-NLP/13-TextRep/assignment.md
index 52e59e96..b86b4ac4 100644
--- a/translations/no/lessons/5-NLP/13-TextRep/assignment.md
+++ b/translations/no/lessons/5-NLP/13-TextRep/assignment.md
@@ -1,12 +1,3 @@
-
# Oppgave: Notatbøker
Bruk notatbøkene som hører til denne leksjonen (enten PyTorch- eller TensorFlow-versjonen), og kjør dem på nytt med ditt eget datasett, kanskje et fra Kaggle, brukt med kildehenvisning. Skriv om notatboken for å fremheve dine egne funn. Prøv noen innovative datasett som kan være overraskende, for eksempel [dette om UFO-observasjoner](https://www.kaggle.com/datasets/NUFORC/ufo-sightings) fra NUFORC.
diff --git a/translations/no/lessons/5-NLP/14-Embeddings/README.md b/translations/no/lessons/5-NLP/14-Embeddings/README.md
index 98b03b16..211aebdd 100644
--- a/translations/no/lessons/5-NLP/14-Embeddings/README.md
+++ b/translations/no/lessons/5-NLP/14-Embeddings/README.md
@@ -1,12 +1,3 @@
-
# Innebygginger
## [Quiz før forelesning](https://ff-quizzes.netlify.app/en/ai/quiz/27)
diff --git a/translations/no/lessons/5-NLP/14-Embeddings/assignment.md b/translations/no/lessons/5-NLP/14-Embeddings/assignment.md
index b7e8fc8d..94801912 100644
--- a/translations/no/lessons/5-NLP/14-Embeddings/assignment.md
+++ b/translations/no/lessons/5-NLP/14-Embeddings/assignment.md
@@ -1,12 +1,3 @@
-
# Oppgave: Notatbøker
Bruk notatbøkene som er knyttet til denne leksjonen (enten PyTorch- eller TensorFlow-versjonen), og kjør dem på nytt med ditt eget datasett, kanskje et fra Kaggle, brukt med kildehenvisning. Skriv om notatboken for å fremheve dine egne funn. Prøv en annen type datasett og dokumenter funnene dine, ved å bruke tekst som [disse Beatles-tekstene](https://www.kaggle.com/datasets/jenlooper/beatles-lyrics).
diff --git a/translations/no/lessons/5-NLP/15-LanguageModeling/README.md b/translations/no/lessons/5-NLP/15-LanguageModeling/README.md
index 2f169b4a..308a1708 100644
--- a/translations/no/lessons/5-NLP/15-LanguageModeling/README.md
+++ b/translations/no/lessons/5-NLP/15-LanguageModeling/README.md
@@ -1,12 +1,3 @@
-
# Språkmodellering
Semantiske embeddinger, som Word2Vec og GloVe, er faktisk et første steg mot **språkmodellering** - å lage modeller som på en eller annen måte *forstår* (eller *representerer*) språkets natur.
diff --git a/translations/no/lessons/5-NLP/15-LanguageModeling/lab/README.md b/translations/no/lessons/5-NLP/15-LanguageModeling/lab/README.md
index 8cadbd69..0aacd7ef 100644
--- a/translations/no/lessons/5-NLP/15-LanguageModeling/lab/README.md
+++ b/translations/no/lessons/5-NLP/15-LanguageModeling/lab/README.md
@@ -1,12 +1,3 @@
-
# Trene Skip-Gram-modell
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/5-NLP/16-RNN/README.md b/translations/no/lessons/5-NLP/16-RNN/README.md
index 5124a725..68e3928e 100644
--- a/translations/no/lessons/5-NLP/16-RNN/README.md
+++ b/translations/no/lessons/5-NLP/16-RNN/README.md
@@ -1,12 +1,3 @@
-
# Rekurrente Nevrale Nettverk
## [Quiz før forelesning](https://ff-quizzes.netlify.app/en/ai/quiz/31)
@@ -31,7 +22,7 @@ La oss se hvordan en enkel RNN-celle er organisert. Den aksepterer den forrige t
En enkel RNN-celle har to vektmatriser inni: én transformerer et input-symbol (la oss kalle den W), og en annen transformerer en input-tilstand (H). I dette tilfellet beregnes output fra nettverket som σ(W×Xi+H×Si-1+b), der σ er aktiveringsfunksjonen og b er en ekstra bias.
-
+
> Bilde av forfatteren
diff --git a/translations/no/lessons/5-NLP/16-RNN/assignment.md b/translations/no/lessons/5-NLP/16-RNN/assignment.md
index c003c844..ff1b3a28 100644
--- a/translations/no/lessons/5-NLP/16-RNN/assignment.md
+++ b/translations/no/lessons/5-NLP/16-RNN/assignment.md
@@ -1,12 +1,3 @@
-
# Oppgave: Notatbøker
Bruk notatbøkene som hører til denne leksjonen (enten PyTorch- eller TensorFlow-versjonen), og kjør dem på nytt med ditt eget datasett, kanskje et fra Kaggle, brukt med kildehenvisning. Skriv om notatboken for å fremheve dine egne funn. Prøv en annen type datasett og dokumenter funnene dine, ved å bruke tekst som [dette Kaggle-konkurransedatasettet om vær-tweets](https://www.kaggle.com/competitions/crowdflower-weather-twitter/data?select=train.csv).
diff --git a/translations/no/lessons/5-NLP/17-GenerativeNetworks/README.md b/translations/no/lessons/5-NLP/17-GenerativeNetworks/README.md
index 934d7afd..c7277ac6 100644
--- a/translations/no/lessons/5-NLP/17-GenerativeNetworks/README.md
+++ b/translations/no/lessons/5-NLP/17-GenerativeNetworks/README.md
@@ -1,12 +1,3 @@
-
# Generative nettverk
## [Quiz før forelesning](https://ff-quizzes.netlify.app/en/ai/quiz/33)
@@ -36,7 +27,7 @@ Vi vil trene denne RNN-en til å generere tekst steg for steg. På hvert steg ta
Når vi genererer tekst (under inferens), starter vi med en **prompt**, som sendes gjennom RNN-celler for å generere dens mellomliggende tilstand, og deretter starter genereringen fra denne tilstanden. Vi genererer ett tegn om gangen og sender tilstanden og det genererte tegnet til en annen RNN-celle for å generere det neste, helt til vi har generert nok tegn.
-
+
> Bilde av forfatteren
diff --git a/translations/no/lessons/5-NLP/17-GenerativeNetworks/lab/README.md b/translations/no/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
index 7059ab01..4d6c0d39 100644
--- a/translations/no/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
+++ b/translations/no/lessons/5-NLP/17-GenerativeNetworks/lab/README.md
@@ -1,12 +1,3 @@
-
# Ord-nivå Tekstgenerering med RNN-er
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/5-NLP/18-Transformers/README.md b/translations/no/lessons/5-NLP/18-Transformers/README.md
index a7b369d3..99663568 100644
--- a/translations/no/lessons/5-NLP/18-Transformers/README.md
+++ b/translations/no/lessons/5-NLP/18-Transformers/README.md
@@ -1,12 +1,3 @@
-
# Oppmerksomhetsmekanismer og Transformere
## [Quiz før forelesning](https://ff-quizzes.netlify.app/en/ai/quiz/35)
@@ -56,7 +47,7 @@ Ideen med posisjonskoding er som følger:
* Trenbar embedding, lik token-embedding. Dette er tilnærmingen vi vurderer her. Vi bruker embedding-lag på både tokenene og deres posisjoner, noe som resulterer i embedding-vektorer med samme dimensjoner, som vi deretter legger sammen.
* Fast posisjonskodingsfunksjon, som foreslått i den originale artikkelen.
-
+
> Bilde av forfatteren
diff --git a/translations/no/lessons/5-NLP/18-Transformers/assignment.md b/translations/no/lessons/5-NLP/18-Transformers/assignment.md
index 6a1c1437..e99364be 100644
--- a/translations/no/lessons/5-NLP/18-Transformers/assignment.md
+++ b/translations/no/lessons/5-NLP/18-Transformers/assignment.md
@@ -1,12 +1,3 @@
-
# Oppgave: Transformers
Eksperimenter med Transformers på HuggingFace! Prøv noen av skriptene de tilbyr for å jobbe med de ulike modellene som er tilgjengelige på deres nettsted: https://huggingface.co/docs/transformers/run_scripts. Test et av datasettene deres, og importer deretter et eget fra dette pensumet eller fra Kaggle for å se om du kan generere interessante tekster. Lag en notatbok med dine funn.
diff --git a/translations/no/lessons/5-NLP/19-NER/README.md b/translations/no/lessons/5-NLP/19-NER/README.md
index 5afa1890..f909a6d9 100644
--- a/translations/no/lessons/5-NLP/19-NER/README.md
+++ b/translations/no/lessons/5-NLP/19-NER/README.md
@@ -1,12 +1,3 @@
-
# Navngitt Enhetsgjenkjenning
Hittil har vi stort sett fokusert på én NLP-oppgave - klassifisering. Det finnes imidlertid også andre NLP-oppgaver som kan løses med nevrale nettverk. En av disse oppgavene er **[Navngitt Enhetsgjenkjenning](https://wikipedia.org/wiki/Named-entity_recognition)** (NER), som handler om å gjenkjenne spesifikke enheter i tekst, som steder, personnavn, tidsintervaller, kjemiske formler og lignende.
@@ -17,7 +8,7 @@ Hittil har vi stort sett fokusert på én NLP-oppgave - klassifisering. Det finn
La oss si at du ønsker å utvikle en naturlig språk-chatbot, lik Amazon Alexa eller Google Assistant. Intelligente chatboter fungerer ved å *forstå* hva brukeren ønsker, gjennom tekstklassifisering av den innsendte setningen. Resultatet av denne klassifiseringen er den såkalte **intensjonen**, som avgjør hva chatboten skal gjøre.
-
+
> Bilde av forfatteren
diff --git a/translations/no/lessons/5-NLP/19-NER/lab/README.md b/translations/no/lessons/5-NLP/19-NER/lab/README.md
index 970a52cb..323a3655 100644
--- a/translations/no/lessons/5-NLP/19-NER/lab/README.md
+++ b/translations/no/lessons/5-NLP/19-NER/lab/README.md
@@ -1,12 +1,3 @@
-
# NER
Laboppgave fra [AI for Beginners Curriculum](https://github.com/microsoft/ai-for-beginners).
diff --git a/translations/no/lessons/5-NLP/20-LangModels/README.md b/translations/no/lessons/5-NLP/20-LangModels/README.md
index 1b253558..f0392a56 100644
--- a/translations/no/lessons/5-NLP/20-LangModels/README.md
+++ b/translations/no/lessons/5-NLP/20-LangModels/README.md
@@ -1,12 +1,3 @@
-
# Forhåndstrente store språkmodeller
I alle våre tidligere oppgaver trente vi et nevralt nettverk for å utføre en bestemt oppgave ved hjelp av et merket datasett. Med store transformer-modeller, som BERT, bruker vi språklæring i en selv-supervisert tilnærming for å bygge en språkmodell, som deretter spesialiseres for spesifikke oppgaver gjennom videre domenespesifikk trening. Det har imidlertid blitt vist at store språkmodeller også kan løse mange oppgaver uten NOEN domenespesifikk trening. En familie av modeller som kan gjøre dette kalles **GPT**: Generative Pre-Trained Transformer.
diff --git a/translations/no/lessons/5-NLP/README.md b/translations/no/lessons/5-NLP/README.md
index b1d1f29f..e63e20d7 100644
--- a/translations/no/lessons/5-NLP/README.md
+++ b/translations/no/lessons/5-NLP/README.md
@@ -1,12 +1,3 @@
-
# Naturlig Språkbehandling
diff --git a/translations/no/lessons/6-Other/21-GeneticAlgorithms/README.md b/translations/no/lessons/6-Other/21-GeneticAlgorithms/README.md
index 3cf129bb..a9973e05 100644
--- a/translations/no/lessons/6-Other/21-GeneticAlgorithms/README.md
+++ b/translations/no/lessons/6-Other/21-GeneticAlgorithms/README.md
@@ -1,12 +1,3 @@
-
# Genetiske Algoritmer
## [Quiz før forelesning](https://ff-quizzes.netlify.app/en/ai/quiz/41)
diff --git a/translations/no/lessons/6-Other/22-DeepRL/README.md b/translations/no/lessons/6-Other/22-DeepRL/README.md
index 4c8ee8b0..634bd59e 100644
--- a/translations/no/lessons/6-Other/22-DeepRL/README.md
+++ b/translations/no/lessons/6-Other/22-DeepRL/README.md
@@ -1,12 +1,3 @@
-
# Dyp Forsterkningslæring
Forsterkningslæring (RL) regnes som en av de grunnleggende paradigmer innen maskinlæring, ved siden av veiledet læring og uveiledet læring. Mens vi i veiledet læring baserer oss på datasett med kjente utfall, er RL basert på **læring gjennom handling**. For eksempel, når vi ser et dataspill for første gang, begynner vi å spille, selv uten å kjenne reglene, og snart blir vi bedre bare ved å spille og justere oppførselen vår.
@@ -34,7 +25,7 @@ Dere har sikkert sett moderne balanseringsenheter som *Segway* eller *Gyroscoote
En forenklet versjon av balansering er kjent som **CartPole**-problemet. I CartPole-verdenen har vi en horisontal skyver som kan bevege seg til venstre eller høyre, og målet er å balansere en vertikal stang på toppen av skyveren mens den beveger seg.
-
+
For å opprette og bruke dette miljøet trenger vi noen få linjer med Python-kode:
diff --git a/translations/no/lessons/6-Other/22-DeepRL/lab/README.md b/translations/no/lessons/6-Other/22-DeepRL/lab/README.md
index 17c5c9d9..c922d623 100644
--- a/translations/no/lessons/6-Other/22-DeepRL/lab/README.md
+++ b/translations/no/lessons/6-Other/22-DeepRL/lab/README.md
@@ -1,12 +1,3 @@
-
## Miljøet
Mountain Car-miljøet består av en bil som sitter fast i en dal. Målet ditt er å hoppe ut av dalen og nå flagget. Handlingene du kan utføre er å akselerere til venstre, til høyre, eller ikke gjøre noe. Du kan observere bilens posisjon langs x-aksen og hastigheten.
diff --git a/translations/no/lessons/6-Other/23-MultiagentSystems/README.md b/translations/no/lessons/6-Other/23-MultiagentSystems/README.md
index cac620aa..b2c02a84 100644
--- a/translations/no/lessons/6-Other/23-MultiagentSystems/README.md
+++ b/translations/no/lessons/6-Other/23-MultiagentSystems/README.md
@@ -1,12 +1,3 @@
-
# Multi-Agent Systemer
En av de mulige måtene å oppnå intelligens på er den såkalte **emergente** (eller **synergetiske**) tilnærmingen, som er basert på det faktum at den kombinerte oppførselen til mange relativt enkle agenter kan resultere i en mer kompleks (eller intelligent) oppførsel av systemet som helhet. Teoretisk sett er dette basert på prinsippene for [Kollektiv intelligens](https://en.wikipedia.org/wiki/Collective_intelligence), [Emergentisme](https://en.wikipedia.org/wiki/Global_brain) og [Evolusjonær kybernetikk](https://en.wikipedia.org/wiki/Global_brain), som sier at systemer på høyere nivå får en form for merverdi når de kombineres riktig fra systemer på lavere nivå (det såkalte *prinsippet om metasystemovergang*).
@@ -60,7 +51,7 @@ Du kan [laste ned](https://ccl.northwestern.edu/netlogo/download.shtml) og insta
En flott ting med NetLogo er at det inneholder et bibliotek med fungerende modeller som du kan prøve. Gå til **File → Models Library**, og du har mange kategorier med modeller å velge mellom.
-
+
> Et skjermbilde av modellbiblioteket av Dmitry Soshnikov
diff --git a/translations/no/lessons/6-Other/23-MultiagentSystems/assignment.md b/translations/no/lessons/6-Other/23-MultiagentSystems/assignment.md
index 35ec312d..97d715c2 100644
--- a/translations/no/lessons/6-Other/23-MultiagentSystems/assignment.md
+++ b/translations/no/lessons/6-Other/23-MultiagentSystems/assignment.md
@@ -1,12 +1,3 @@
-
# NetLogo-oppgave
Ta en av modellene i NetLogos bibliotek og bruk den til å simulere en virkelighetstro situasjon så nøyaktig som mulig. Et godt eksempel kan være å justere Virus-modellen i mappen Alternative Visualizations for å vise hvordan den kan brukes til å modellere spredningen av COVID-19. Kan du lage en modell som etterligner en virkelig virussmitte?
diff --git a/translations/no/lessons/7-Ethics/README.md b/translations/no/lessons/7-Ethics/README.md
index 09fe706a..48144b3e 100644
--- a/translations/no/lessons/7-Ethics/README.md
+++ b/translations/no/lessons/7-Ethics/README.md
@@ -1,12 +1,3 @@
-
# Etisk og Ansvarlig AI
Du er nesten ferdig med dette kurset, og jeg håper at du nå tydelig ser at AI er basert på en rekke formelle matematiske metoder som lar oss finne sammenhenger i data og trene modeller til å etterligne noen aspekter av menneskelig atferd. På dette tidspunktet i historien anser vi AI som et svært kraftig verktøy for å trekke ut mønstre fra data og bruke disse mønstrene til å løse nye problemer.
diff --git a/translations/no/lessons/README.md b/translations/no/lessons/README.md
index 6eabc81b..0f745ade 100644
--- a/translations/no/lessons/README.md
+++ b/translations/no/lessons/README.md
@@ -1,12 +1,3 @@
-
# Oversikt
diff --git a/translations/no/lessons/X-Extras/X1-MultiModal/README.md b/translations/no/lessons/X-Extras/X1-MultiModal/README.md
index 697c7996..33f81fca 100644
--- a/translations/no/lessons/X-Extras/X1-MultiModal/README.md
+++ b/translations/no/lessons/X-Extras/X1-MultiModal/README.md
@@ -1,12 +1,3 @@
-
# Multi-Modale Nettverk
Etter suksessen med transformer-modeller for å løse NLP-oppgaver, har de samme eller lignende arkitekturer blitt brukt på oppgaver innen datamaskinsyn. Det er økende interesse for å bygge modeller som kan *kombinere* visuelle og språklige evner. En av disse forsøkene ble gjort av OpenAI, og kalles CLIP og DALL.E.
diff --git a/translations/no/lessons/sketchnotes/LICENSE.md b/translations/no/lessons/sketchnotes/LICENSE.md
index 4e49be5c..6dbd40f9 100644
--- a/translations/no/lessons/sketchnotes/LICENSE.md
+++ b/translations/no/lessons/sketchnotes/LICENSE.md
@@ -1,12 +1,3 @@
-
Attribution-ShareAlike 4.0 Internasjonal
=======================================================================
diff --git a/translations/no/lessons/sketchnotes/README.md b/translations/no/lessons/sketchnotes/README.md
index 1d3be8ca..ecc71cbf 100644
--- a/translations/no/lessons/sketchnotes/README.md
+++ b/translations/no/lessons/sketchnotes/README.md
@@ -1,12 +1,3 @@
-
Alle sketchnotes for pensum kan lastes ned her.
🎨 Laget av: Tomomi Imura (Twitter: [@girlie_mac](https://twitter.com/girlie_mac), GitHub: [girliemac](https://github.com/girliemac))
diff --git a/translations/no/troubleshoot.md b/translations/no/troubleshoot.md
index ed7a13c0..2e4555d1 100644
--- a/translations/no/troubleshoot.md
+++ b/translations/no/troubleshoot.md
@@ -1,12 +1,3 @@
-
# AI-For-Beginners Feilsøkingsguide
Denne guiden hjelper deg med å løse vanlige problemer som oppstår når du bruker eller bidrar til [AI-For-Beginners](https://github.com/microsoft/AI-For-Beginners)-repositoryet. Hvert problem inkluderer bakgrunn, symptomer, forklaringer og trinnvise løsninger.